├── .dockerignore ├── .gitignore ├── Dockerfile ├── KernelBench ├── level1 │ ├── 100_HingeLoss.py │ ├── 10_3D_tensor_matrix_multiplication.py │ ├── 11_4D_tensor_matrix_multiplication.py │ ├── 12_Matmul_with_diagonal_matrices_.py │ ├── 13_Matmul_for_symmetric_matrices.py │ ├── 14_Matmul_for_upper_triangular_matrices.py │ ├── 15_Matmul_for_lower_triangular_matrices.py │ ├── 16_Matmul_with_transposed_A.py │ ├── 17_Matmul_with_transposed_B.py │ ├── 18_Matmul_with_transposed_both.py │ ├── 19_ReLU.py │ ├── 1_Square_matrix_multiplication_.py │ ├── 20_LeakyReLU.py │ ├── 21_Sigmoid.py │ ├── 22_Tanh.py │ ├── 23_Softmax.py │ ├── 24_LogSoftmax.py │ ├── 25_Swish.py │ ├── 26_GELU_.py │ ├── 27_SELU_.py │ ├── 28_HardSigmoid.py │ ├── 29_Softplus.py │ ├── 2_Standard_matrix_multiplication_.py │ ├── 30_Softsign.py │ ├── 31_ELU.py │ ├── 32_HardTanh.py │ ├── 33_BatchNorm.py │ ├── 34_InstanceNorm.py │ ├── 35_GroupNorm_.py │ ├── 36_RMSNorm_.py │ ├── 37_FrobeniusNorm_.py │ ├── 38_L1Norm_.py │ ├── 39_L2Norm_.py │ ├── 3_Batched_matrix_multiplication.py │ ├── 40_LayerNorm.py │ ├── 41_Max_Pooling_1D.py │ ├── 42_Max_Pooling_2D.py │ ├── 43_Max_Pooling_3D.py │ ├── 44_Average_Pooling_1D.py │ ├── 45_Average_Pooling_2D.py │ ├── 46_Average_Pooling_3D.py │ ├── 47_Sum_reduction_over_a_dimension.py │ ├── 48_Mean_reduction_over_a_dimension.py │ ├── 49_Max_reduction_over_a_dimension.py │ ├── 4_Matrix_vector_multiplication_.py │ ├── 50_Product_reduction_over_a_dimension.py │ ├── 51_Argmax_over_a_dimension.py │ ├── 52_Argmin_over_a_dimension.py │ ├── 53_Min_reduction_over_a_dimension.py │ ├── 54_conv_standard_3D__square_input__square_kernel.py │ ├── 55_conv_standard_2D__asymmetric_input__square_kernel.py │ ├── 56_conv_standard_2D__asymmetric_input__asymmetric_kernel.py │ ├── 57_conv_transposed_2D__square_input__square_kernel.py │ ├── 58_conv_transposed_3D__asymmetric_input__asymmetric_kernel.py │ ├── 59_conv_standard_3D__asymmetric_input__square_kernel.py │ ├── 5_Matrix_scalar_multiplication.py │ ├── 60_conv_standard_3D__square_input__asymmetric_kernel.py │ ├── 61_conv_transposed_3D__square_input__square_kernel.py │ ├── 62_conv_standard_2D__square_input__asymmetric_kernel.py │ ├── 63_conv_standard_2D__square_input__square_kernel.py │ ├── 64_conv_transposed_1D.py │ ├── 65_conv_transposed_2D__square_input__asymmetric_kernel.py │ ├── 66_conv_standard_3D__asymmetric_input__asymmetric_kernel.py │ ├── 67_conv_standard_1D.py │ ├── 68_conv_transposed_3D__square_input__asymmetric_kernel.py │ ├── 69_conv_transposed_2D__asymmetric_input__asymmetric_kernel.py │ ├── 6_Matmul_with_large_K_dimension_.py │ ├── 70_conv_transposed_3D__asymmetric_input__square_kernel.py │ ├── 71_conv_transposed_2D__asymmetric_input__square_kernel.py │ ├── 72_conv_transposed_3D_asymmetric_input_asymmetric_kernel___strided_padded_grouped_.py │ ├── 73_conv_transposed_3D_asymmetric_input_square_kernel__strided_padded__grouped.py │ ├── 74_conv_transposed_1D_dilated.py │ ├── 75_conv_transposed_2D_asymmetric_input_asymmetric_kernel_strided__grouped____padded____dilated__.py │ ├── 76_conv_standard_1D_dilated_strided__.py │ ├── 77_conv_transposed_3D_square_input_square_kernel___padded____dilated____strided__.py │ ├── 78_conv_transposed_2D_asymmetric_input_asymmetric_kernel___padded__.py │ ├── 79_conv_transposed_1D_asymmetric_input_square_kernel___padded____strided____dilated__.py │ ├── 7_Matmul_with_small_K_dimension_.py │ ├── 80_conv_standard_2D_square_input_asymmetric_kernel___dilated____padded__.py │ ├── 81_conv_transposed_2D_asymmetric_input_square_kernel___dilated____padded____strided__.py │ ├── 82_conv_depthwise_2D_square_input_square_kernel.py │ ├── 83_conv_depthwise_2D_square_input_asymmetric_kernel.py │ ├── 84_conv_depthwise_2D_asymmetric_input_square_kernel.py │ ├── 85_conv_depthwise_2D_asymmetric_input_asymmetric_kernel.py │ ├── 86_conv_depthwise_separable_2D.py │ ├── 87_conv_pointwise_2D.py │ ├── 88_MinGPTNewGelu.py │ ├── 89_cumsum.py │ ├── 8_Matmul_with_irregular_shapes_.py │ ├── 90_cumprod.py │ ├── 91_cumsum_reverse.py │ ├── 92_cumsum_exclusive.py │ ├── 93_masked_cumsum.py │ ├── 94_MSELoss.py │ ├── 95_CrossEntropyLoss.py │ ├── 96_HuberLoss.py │ ├── 97_CosineSimilarityLoss.py │ ├── 98_KLDivLoss.py │ ├── 99_TripletMarginLoss.py │ └── 9_Tall_skinny_matrix_multiplication_.py ├── level2 │ ├── 100_ConvTranspose3d_Clamp_Min_Divide.py │ ├── 10_ConvTranspose2d_MaxPool_Hardtanh_Mean_Tanh.py │ ├── 11_ConvTranspose2d_BatchNorm_Tanh_MaxPool_GroupNorm.py │ ├── 12_Gemm_Multiply_LeakyReLU.py │ ├── 13_ConvTranspose3d_Mean_Add_Softmax_Tanh_Scaling.py │ ├── 14_Gemm_Divide_Sum_Scaling.py │ ├── 15_ConvTranspose3d_BatchNorm_Subtract.py │ ├── 16_ConvTranspose2d_Mish_Add_Hardtanh_Scaling.py │ ├── 17_Conv2d_InstanceNorm_Divide.py │ ├── 18_Matmul_Sum_Max_AvgPool_LogSumExp_LogSumExp.py │ ├── 19_ConvTranspose2d_GELU_GroupNorm.py │ ├── 1_Conv2D_ReLU_BiasAdd.py │ ├── 20_ConvTranspose3d_Sum_ResidualAdd_Multiply_ResidualAdd.py │ ├── 21_Conv2d_Add_Scale_Sigmoid_GroupNorm.py │ ├── 22_Matmul_Scale_ResidualAdd_Clamp_LogSumExp_Mish.py │ ├── 23_Conv3d_GroupNorm_Mean.py │ ├── 24_Conv3d_Min_Softmax.py │ ├── 25_Conv2d_Min_Tanh_Tanh.py │ ├── 26_ConvTranspose3d_Add_HardSwish.py │ ├── 27_Conv3d_HardSwish_ReLU_Softmax_Mean.py │ ├── 28_BMM_InstanceNorm_Sum_ResidualAdd_Multiply.py │ ├── 29_Matmul_Mish_Mish.py │ ├── 2_ConvTranspose2d_BiasAdd_Clamp_Scaling_Clamp_Divide.py │ ├── 30_Gemm_GroupNorm_Hardtanh.py │ ├── 31_Conv2d_Min_Add_Multiply.py │ ├── 32_Conv2d_Scaling_Min.py │ ├── 33_Gemm_Scale_BatchNorm.py │ ├── 34_ConvTranspose3d_LayerNorm_GELU_Scaling.py │ ├── 35_Conv2d_Subtract_HardSwish_MaxPool_Mish.py │ ├── 36_ConvTranspose2d_Min_Sum_GELU_Add.py │ ├── 37_Matmul_Swish_Sum_GroupNorm.py │ ├── 38_ConvTranspose3d_AvgPool_Clamp_Softmax_Multiply.py │ ├── 39_Gemm_Scale_BatchNorm.py │ ├── 3_ConvTranspose3d_Sum_LayerNorm_AvgPool_GELU.py │ ├── 40_Matmul_Scaling_ResidualAdd.py │ ├── 41_Gemm_BatchNorm_GELU_GroupNorm_Mean_ReLU.py │ ├── 42_ConvTranspose2d_GlobalAvgPool_BiasAdd_LogSumExp_Sum_Multiply.py │ ├── 43_Conv3d_Max_LogSumExp_ReLU.py │ ├── 44_ConvTranspose2d_Multiply_GlobalAvgPool_GlobalAvgPool_Mean.py │ ├── 45_Gemm_Sigmoid_Sum_LogSumExp.py │ ├── 46_Conv2d_Subtract_Tanh_Subtract_AvgPool.py │ ├── 47_Conv3d_Mish_Tanh.py │ ├── 48_Conv3d_Scaling_Tanh_Multiply_Sigmoid.py │ ├── 49_ConvTranspose3d_Softmax_Sigmoid.py │ ├── 4_Conv2d_Mish_Mish.py │ ├── 50_ConvTranspose3d_Scaling_AvgPool_BiasAdd_Scaling.py │ ├── 51_Gemm_Subtract_GlobalAvgPool_LogSumExp_GELU_ResidualAdd.py │ ├── 52_Conv2d_Activation_BatchNorm.py │ ├── 53_Gemm_Scaling_Hardtanh_GELU.py │ ├── 54_Conv2d_Multiply_LeakyReLU_GELU.py │ ├── 55_Matmul_MaxPool_Sum_Scale.py │ ├── 56_Matmul_Sigmoid_Sum.py │ ├── 57_Conv2d_ReLU_HardSwish.py │ ├── 58_ConvTranspose3d_LogSumExp_HardSwish_Subtract_Clamp_Max.py │ ├── 59_Matmul_Swish_Scaling.py │ ├── 5_ConvTranspose2d_Subtract_Tanh.py │ ├── 60_ConvTranspose3d_Swish_GroupNorm_HardSwish.py │ ├── 61_ConvTranspose3d_ReLU_GroupNorm.py │ ├── 62_Matmul_GroupNorm_LeakyReLU_Sum.py │ ├── 63_Gemm_ReLU_Divide.py │ ├── 64_Gemm_LogSumExp_LeakyReLU_LeakyReLU_GELU_GELU.py │ ├── 65_Conv2d_AvgPool_Sigmoid_Sum.py │ ├── 66_Matmul_Dropout_Mean_Softmax.py │ ├── 67_Conv2d_GELU_GlobalAvgPool.py │ ├── 68_Matmul_Min_Subtract.py │ ├── 69_Conv2d_HardSwish_ReLU.py │ ├── 6_Conv3d_Softmax_MaxPool_MaxPool.py │ ├── 70_Gemm_Sigmoid_Scaling_ResidualAdd.py │ ├── 71_Conv2d_Divide_LeakyReLU.py │ ├── 72_ConvTranspose3d_BatchNorm_AvgPool_AvgPool.py │ ├── 73_Conv2d_BatchNorm_Scaling.py │ ├── 74_ConvTranspose3d_LeakyReLU_Multiply_LeakyReLU_Max.py │ ├── 75_Gemm_GroupNorm_Min_BiasAdd.py │ ├── 76_Gemm_Add_ReLU.py │ ├── 77_ConvTranspose3d_Scale_BatchNorm_GlobalAvgPool.py │ ├── 78_ConvTranspose3d_Max_Max_Sum.py │ ├── 79_Conv3d_Multiply_InstanceNorm_Clamp_Multiply_Max.py │ ├── 7_Conv3d_ReLU_LeakyReLU_GELU_Sigmoid_BiasAdd.py │ ├── 80_Gemm_Max_Subtract_GELU.py │ ├── 81_Gemm_Swish_Divide_Clamp_Tanh_Clamp.py │ ├── 82_Conv2d_Tanh_Scaling_BiasAdd_Max.py │ ├── 83_Conv3d_GroupNorm_Min_Clamp_Dropout.py │ ├── 84_Gemm_BatchNorm_Scaling_Softmax.py │ ├── 85_Conv2d_GroupNorm_Scale_MaxPool_Clamp.py │ ├── 86_Matmul_Divide_GELU.py │ ├── 87_Conv2d_Subtract_Subtract_Mish.py │ ├── 88_Gemm_GroupNorm_Swish_Multiply_Swish.py │ ├── 89_ConvTranspose3d_MaxPool_Softmax_Subtract_Swish_Max.py │ ├── 8_Conv3d_Divide_Max_GlobalAvgPool_BiasAdd_Sum.py │ ├── 90_Conv3d_LeakyReLU_Sum_Clamp_GELU.py │ ├── 91_ConvTranspose2d_Softmax_BiasAdd_Scaling_Sigmoid.py │ ├── 92_Conv2d_GroupNorm_Tanh_HardSwish_ResidualAdd_LogSumExp.py │ ├── 93_ConvTranspose2d_Add_Min_GELU_Multiply.py │ ├── 94_Gemm_BiasAdd_Hardtanh_Mish_GroupNorm.py │ ├── 95_Matmul_Add_Swish_Tanh_GELU_Hardtanh.py │ ├── 96_ConvTranspose3d_Multiply_Max_GlobalAvgPool_Clamp.py │ ├── 97_Matmul_BatchNorm_BiasAdd_Divide_Swish.py │ ├── 98_Matmul_AvgPool_GELU_Scale_Max.py │ ├── 99_Matmul_GELU_Softmax.py │ └── 9_Matmul_Subtract_Multiply_ReLU.py ├── level3 │ ├── 10_ResNet101.py │ ├── 11_VGG16.py │ ├── 12_VGG19.py │ ├── 13_DenseNet121TransitionLayer.py │ ├── 14_DenseNet121DenseBlock.py │ ├── 15_DenseNet121.py │ ├── 16_DenseNet201.py │ ├── 17_SqueezeNetFireModule.py │ ├── 18_SqueezeNet.py │ ├── 19_MobileNetV1.py │ ├── 1_MLP.py │ ├── 20_MobileNetV2.py │ ├── 21_EfficientNetMBConv.py │ ├── 22_EfficientNetB0.py │ ├── 23_EfficientNetB1.py │ ├── 24_EfficientNetB2.py │ ├── 25_ShuffleNetUnit.py │ ├── 26_ShuffleNet.py │ ├── 27_RegNet.py │ ├── 28_VisionTransformer.py │ ├── 29_SwinMLP.py │ ├── 2_ShallowWideMLP.py │ ├── 30_SwinTransformerV2.py │ ├── 31_VisionAttention.py │ ├── 32_ConvolutionalVisionTransformer.py │ ├── 33_VanillaRNN.py │ ├── 34_VanillaRNNHidden.py │ ├── 35_LTSM.py │ ├── 36_LTSMHn.py │ ├── 37_LTSMCn.py │ ├── 38_LTSMBidirectional.py │ ├── 39_GRU.py │ ├── 3_DeepNarrowMLP.py │ ├── 40_GRUHidden.py │ ├── 41_GRUBirectional.py │ ├── 42_GRUBidirectionalHidden.py │ ├── 43_MinGPTCausalAttention.py │ ├── 44_MiniGPTBlock.py │ ├── 45_UNetSoftmax.py │ ├── 46_NetVladWithGhostClusters.py │ ├── 47_NetVladNoGhostClusters.py │ ├── 48_Mamba2ReturnY.py │ ├── 49_Mamba2ReturnFinalState.py │ ├── 4_LeNet5.py │ ├── 50_ReLUSelfAttention.py │ ├── 5_AlexNet.py │ ├── 6_GoogleNetInceptionModule.py │ ├── 7_GoogleNetInceptionV1.py │ ├── 8_ResNetBasicBlock.py │ └── 9_ResNet18.py └── level4 │ ├── 10_google-bigbird-roberta-base_bs1024_seq32.py │ ├── 11_google-electra-small-discriminator_bs1_seq511.py │ ├── 12_google-electra-small-discriminator_bs1024_seq32.py │ ├── 13_google-reformer-enwik8_bs32_seq256.py │ ├── 14_google-electra-small-discriminator_bs32_seq256.py │ ├── 15_google-reformer-enwik8_bs1024_seq32.py │ ├── 16_gpt2_bs1_seq1023.py │ ├── 17_facebook-bart-large_bs1024_seq32.py │ ├── 18_EleutherAI-gpt-neo-2p7B_bs512_seq32.py │ ├── 19_gpt2_bs1024_seq32.py │ ├── 1_EleutherAI-gpt-neo-2p7B_bs32_seq256.py │ ├── 20_facebook-bart-large_bs32_seq256.py │ ├── 2_facebook-opt-1p3b_bs1_seq2047.py │ ├── 3_EleutherAI-gpt-neo-2p7B_bs1_seq2047.py │ ├── 4_facebook-opt-1p3b_bs32_seq256.py │ ├── 5_google-bigbird-roberta-base_bs1_seq4095.py │ ├── 6_facebook-bart-large_bs1_seq1023.py │ ├── 7_gpt2_bs32_seq256.py │ ├── 8_facebook-opt-1p3b_bs512_seq32.py │ └── 9_google-bigbird-roberta-base_bs32_seq256.py ├── LICENSE ├── README.md ├── TRITON_INTEGRATION_GUIDE.md ├── TRITON_README.md ├── assets └── figures │ ├── KernelBenchMascot.png │ └── KernelBenchWorkFlow.png ├── cursorchanges.md ├── docker-compose.yml ├── eval_py.diff ├── requirements.txt ├── results └── timing │ ├── A100-80GB_modal │ ├── baseline_time_torch.json │ └── baseline_time_torch_compile_inductor_default.json │ ├── A100_modal │ ├── baseline_time_torch.json │ └── baseline_time_torch_compile_inductor_default.json │ ├── A10G_modal │ ├── baseline_time_torch.json │ └── baseline_time_torch_compile_inductor_default.json │ ├── B200_together │ ├── baseline_time_torch.json │ ├── baseline_time_torch_compile_cudagraphs.json │ ├── baseline_time_torch_compile_inductor_default.json │ ├── baseline_time_torch_compile_inductor_max-autotune-no-cudagraphs.json │ ├── baseline_time_torch_compile_inductor_max-autotune.json │ └── baseline_time_torch_compile_inductor_reduce-overhead.json │ ├── H100_together │ ├── baseline_time_torch.json │ ├── baseline_time_torch_compile_cudagraphs.json │ ├── baseline_time_torch_compile_inductor_default.json │ ├── baseline_time_torch_compile_inductor_max-autotune-no-cudagraphs.json │ ├── baseline_time_torch_compile_inductor_max-autotune.json │ └── baseline_time_torch_compile_inductor_reduce-overhead.json │ ├── L40S_matx3 │ ├── baseline_time_torch.json │ ├── baseline_time_torch_compile_cudagraphs.json │ ├── baseline_time_torch_compile_inductor_default.json │ ├── baseline_time_torch_compile_inductor_max-autotune-no-cudagraphs.json │ ├── baseline_time_torch_compile_inductor_max-autotune.json │ └── baseline_time_torch_compile_inductor_reduce-overhead.json │ ├── L40S_modal │ ├── baseline_time_torch.json │ └── baseline_time_torch_compile_inductor_default.json │ ├── L4_modal │ ├── baseline_time_torch.json │ └── baseline_time_torch_compile_inductor_default.json │ ├── README.md │ ├── T4_modal │ ├── baseline_time_torch.json │ └── baseline_time_torch_compile_inductor_default.json │ └── old │ ├── baseline_time_cleaned.json │ ├── baseline_time_matx2.json │ ├── baseline_time_matx3.json │ ├── baseline_time_torch_compile_cleaned.json │ ├── baseline_time_torch_compile_matx2.json │ └── baseline_time_torch_compile_matx3.json ├── run_and_check_triton_py.diff ├── scripts ├── benchmark_eval_analysis.py ├── debug_stddout.py ├── eval_from_generations.py ├── generate_and_eval_single_sample.py ├── generate_and_eval_single_sample_modal.py ├── generate_baseline_time.py ├── generate_baseline_time_modal.py ├── generate_samples.py ├── inspect_baseline.py ├── inspect_kernel_pytorch_profiler.py ├── inspect_triton.py ├── run_and_check.py ├── run_and_check_triton.py ├── verify_bench.py └── verify_generation.py ├── setup.py ├── src ├── __init__.py ├── analysis.py ├── compile.py ├── dataset.py ├── eval.py ├── frameworks.py ├── make_hf_dataset.py ├── prompt_constructor.py ├── prompts │ ├── README.md │ ├── cot │ │ ├── model_cot_fuse_gelu.py │ │ ├── model_cot_mnist2.py │ │ └── model_cot_tiled_matmul.py │ ├── few_shot │ │ ├── model_ex_add.py │ │ ├── model_ex_flash_attn.py │ │ ├── model_ex_fuse_gelu.py │ │ ├── model_ex_mnist2.py │ │ ├── model_ex_tiled_matmul.py │ │ ├── model_new_ex_add.py │ │ ├── model_new_ex_flash_attn.py │ │ ├── model_new_ex_fuse_gelu.py │ │ ├── model_new_ex_mnist2.py │ │ └── model_new_ex_tiled_matmul.py │ ├── hardware │ │ └── gpu_specs.py │ ├── model_ex_0.py │ ├── model_ex_1.py │ ├── model_ex_2.py │ ├── model_ex_add.py │ ├── model_new_ex_0.py │ ├── model_new_ex_1.py │ ├── model_new_ex_2.py │ ├── model_new_ex_add.py │ ├── model_new_ex_add_triton.py │ └── model_new_ex_matmul_triton.py ├── score.py ├── scratch │ ├── log.txt │ ├── model.py │ ├── model_new.py │ ├── prompt.txt │ └── test.py ├── unit_tests │ ├── test_dataset.py │ ├── test_score.py │ └── test_utils.py └── utils.py ├── test_setup.py ├── test_triton_integration.py ├── triton_standard_matmul.py └── triton_test ├── triton_alexnet.py ├── triton_gpt2_passthrough.py ├── triton_matmul_gelu_softmax.py ├── triton_mingpt_causal_attention.py └── triton_relu_kernel.py /.dockerignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/.dockerignore -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/.gitignore -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/Dockerfile -------------------------------------------------------------------------------- /KernelBench/level1/100_HingeLoss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/100_HingeLoss.py -------------------------------------------------------------------------------- /KernelBench/level1/10_3D_tensor_matrix_multiplication.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/10_3D_tensor_matrix_multiplication.py -------------------------------------------------------------------------------- /KernelBench/level1/11_4D_tensor_matrix_multiplication.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/11_4D_tensor_matrix_multiplication.py -------------------------------------------------------------------------------- /KernelBench/level1/12_Matmul_with_diagonal_matrices_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/12_Matmul_with_diagonal_matrices_.py -------------------------------------------------------------------------------- /KernelBench/level1/13_Matmul_for_symmetric_matrices.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/13_Matmul_for_symmetric_matrices.py -------------------------------------------------------------------------------- /KernelBench/level1/14_Matmul_for_upper_triangular_matrices.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/14_Matmul_for_upper_triangular_matrices.py -------------------------------------------------------------------------------- /KernelBench/level1/15_Matmul_for_lower_triangular_matrices.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/15_Matmul_for_lower_triangular_matrices.py -------------------------------------------------------------------------------- /KernelBench/level1/16_Matmul_with_transposed_A.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/16_Matmul_with_transposed_A.py -------------------------------------------------------------------------------- /KernelBench/level1/17_Matmul_with_transposed_B.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/17_Matmul_with_transposed_B.py -------------------------------------------------------------------------------- /KernelBench/level1/18_Matmul_with_transposed_both.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/18_Matmul_with_transposed_both.py -------------------------------------------------------------------------------- /KernelBench/level1/19_ReLU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/19_ReLU.py -------------------------------------------------------------------------------- /KernelBench/level1/1_Square_matrix_multiplication_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/1_Square_matrix_multiplication_.py -------------------------------------------------------------------------------- /KernelBench/level1/20_LeakyReLU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/20_LeakyReLU.py -------------------------------------------------------------------------------- /KernelBench/level1/21_Sigmoid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/21_Sigmoid.py -------------------------------------------------------------------------------- /KernelBench/level1/22_Tanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/22_Tanh.py -------------------------------------------------------------------------------- /KernelBench/level1/23_Softmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/23_Softmax.py -------------------------------------------------------------------------------- /KernelBench/level1/24_LogSoftmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/24_LogSoftmax.py -------------------------------------------------------------------------------- /KernelBench/level1/25_Swish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/25_Swish.py -------------------------------------------------------------------------------- /KernelBench/level1/26_GELU_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/26_GELU_.py -------------------------------------------------------------------------------- /KernelBench/level1/27_SELU_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/27_SELU_.py -------------------------------------------------------------------------------- /KernelBench/level1/28_HardSigmoid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/28_HardSigmoid.py -------------------------------------------------------------------------------- /KernelBench/level1/29_Softplus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/29_Softplus.py -------------------------------------------------------------------------------- /KernelBench/level1/2_Standard_matrix_multiplication_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/2_Standard_matrix_multiplication_.py -------------------------------------------------------------------------------- /KernelBench/level1/30_Softsign.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/30_Softsign.py -------------------------------------------------------------------------------- /KernelBench/level1/31_ELU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/31_ELU.py -------------------------------------------------------------------------------- /KernelBench/level1/32_HardTanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/32_HardTanh.py -------------------------------------------------------------------------------- /KernelBench/level1/33_BatchNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/33_BatchNorm.py -------------------------------------------------------------------------------- /KernelBench/level1/34_InstanceNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/34_InstanceNorm.py -------------------------------------------------------------------------------- /KernelBench/level1/35_GroupNorm_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/35_GroupNorm_.py -------------------------------------------------------------------------------- /KernelBench/level1/36_RMSNorm_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/36_RMSNorm_.py -------------------------------------------------------------------------------- /KernelBench/level1/37_FrobeniusNorm_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/37_FrobeniusNorm_.py -------------------------------------------------------------------------------- /KernelBench/level1/38_L1Norm_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/38_L1Norm_.py -------------------------------------------------------------------------------- /KernelBench/level1/39_L2Norm_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/39_L2Norm_.py -------------------------------------------------------------------------------- /KernelBench/level1/3_Batched_matrix_multiplication.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/3_Batched_matrix_multiplication.py -------------------------------------------------------------------------------- /KernelBench/level1/40_LayerNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/40_LayerNorm.py -------------------------------------------------------------------------------- /KernelBench/level1/41_Max_Pooling_1D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/41_Max_Pooling_1D.py -------------------------------------------------------------------------------- /KernelBench/level1/42_Max_Pooling_2D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/42_Max_Pooling_2D.py -------------------------------------------------------------------------------- /KernelBench/level1/43_Max_Pooling_3D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/43_Max_Pooling_3D.py -------------------------------------------------------------------------------- /KernelBench/level1/44_Average_Pooling_1D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/44_Average_Pooling_1D.py -------------------------------------------------------------------------------- /KernelBench/level1/45_Average_Pooling_2D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/45_Average_Pooling_2D.py -------------------------------------------------------------------------------- /KernelBench/level1/46_Average_Pooling_3D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/46_Average_Pooling_3D.py -------------------------------------------------------------------------------- /KernelBench/level1/47_Sum_reduction_over_a_dimension.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/47_Sum_reduction_over_a_dimension.py -------------------------------------------------------------------------------- /KernelBench/level1/48_Mean_reduction_over_a_dimension.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/48_Mean_reduction_over_a_dimension.py -------------------------------------------------------------------------------- /KernelBench/level1/49_Max_reduction_over_a_dimension.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/49_Max_reduction_over_a_dimension.py -------------------------------------------------------------------------------- /KernelBench/level1/4_Matrix_vector_multiplication_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/4_Matrix_vector_multiplication_.py -------------------------------------------------------------------------------- /KernelBench/level1/50_Product_reduction_over_a_dimension.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/50_Product_reduction_over_a_dimension.py -------------------------------------------------------------------------------- /KernelBench/level1/51_Argmax_over_a_dimension.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/51_Argmax_over_a_dimension.py -------------------------------------------------------------------------------- /KernelBench/level1/52_Argmin_over_a_dimension.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/52_Argmin_over_a_dimension.py -------------------------------------------------------------------------------- /KernelBench/level1/53_Min_reduction_over_a_dimension.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/53_Min_reduction_over_a_dimension.py -------------------------------------------------------------------------------- /KernelBench/level1/54_conv_standard_3D__square_input__square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/54_conv_standard_3D__square_input__square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/55_conv_standard_2D__asymmetric_input__square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/55_conv_standard_2D__asymmetric_input__square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/56_conv_standard_2D__asymmetric_input__asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/56_conv_standard_2D__asymmetric_input__asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/57_conv_transposed_2D__square_input__square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/57_conv_transposed_2D__square_input__square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/58_conv_transposed_3D__asymmetric_input__asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/58_conv_transposed_3D__asymmetric_input__asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/59_conv_standard_3D__asymmetric_input__square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/59_conv_standard_3D__asymmetric_input__square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/5_Matrix_scalar_multiplication.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/5_Matrix_scalar_multiplication.py -------------------------------------------------------------------------------- /KernelBench/level1/60_conv_standard_3D__square_input__asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/60_conv_standard_3D__square_input__asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/61_conv_transposed_3D__square_input__square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/61_conv_transposed_3D__square_input__square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/62_conv_standard_2D__square_input__asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/62_conv_standard_2D__square_input__asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/63_conv_standard_2D__square_input__square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/63_conv_standard_2D__square_input__square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/64_conv_transposed_1D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/64_conv_transposed_1D.py -------------------------------------------------------------------------------- /KernelBench/level1/65_conv_transposed_2D__square_input__asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/65_conv_transposed_2D__square_input__asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/66_conv_standard_3D__asymmetric_input__asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/66_conv_standard_3D__asymmetric_input__asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/67_conv_standard_1D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/67_conv_standard_1D.py -------------------------------------------------------------------------------- /KernelBench/level1/68_conv_transposed_3D__square_input__asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/68_conv_transposed_3D__square_input__asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/69_conv_transposed_2D__asymmetric_input__asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/69_conv_transposed_2D__asymmetric_input__asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/6_Matmul_with_large_K_dimension_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/6_Matmul_with_large_K_dimension_.py -------------------------------------------------------------------------------- /KernelBench/level1/70_conv_transposed_3D__asymmetric_input__square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/70_conv_transposed_3D__asymmetric_input__square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/71_conv_transposed_2D__asymmetric_input__square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/71_conv_transposed_2D__asymmetric_input__square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/72_conv_transposed_3D_asymmetric_input_asymmetric_kernel___strided_padded_grouped_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/72_conv_transposed_3D_asymmetric_input_asymmetric_kernel___strided_padded_grouped_.py -------------------------------------------------------------------------------- /KernelBench/level1/73_conv_transposed_3D_asymmetric_input_square_kernel__strided_padded__grouped.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/73_conv_transposed_3D_asymmetric_input_square_kernel__strided_padded__grouped.py -------------------------------------------------------------------------------- /KernelBench/level1/74_conv_transposed_1D_dilated.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/74_conv_transposed_1D_dilated.py -------------------------------------------------------------------------------- /KernelBench/level1/75_conv_transposed_2D_asymmetric_input_asymmetric_kernel_strided__grouped____padded____dilated__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/75_conv_transposed_2D_asymmetric_input_asymmetric_kernel_strided__grouped____padded____dilated__.py -------------------------------------------------------------------------------- /KernelBench/level1/76_conv_standard_1D_dilated_strided__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/76_conv_standard_1D_dilated_strided__.py -------------------------------------------------------------------------------- /KernelBench/level1/77_conv_transposed_3D_square_input_square_kernel___padded____dilated____strided__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/77_conv_transposed_3D_square_input_square_kernel___padded____dilated____strided__.py -------------------------------------------------------------------------------- /KernelBench/level1/78_conv_transposed_2D_asymmetric_input_asymmetric_kernel___padded__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/78_conv_transposed_2D_asymmetric_input_asymmetric_kernel___padded__.py -------------------------------------------------------------------------------- /KernelBench/level1/79_conv_transposed_1D_asymmetric_input_square_kernel___padded____strided____dilated__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/79_conv_transposed_1D_asymmetric_input_square_kernel___padded____strided____dilated__.py -------------------------------------------------------------------------------- /KernelBench/level1/7_Matmul_with_small_K_dimension_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/7_Matmul_with_small_K_dimension_.py -------------------------------------------------------------------------------- /KernelBench/level1/80_conv_standard_2D_square_input_asymmetric_kernel___dilated____padded__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/80_conv_standard_2D_square_input_asymmetric_kernel___dilated____padded__.py -------------------------------------------------------------------------------- /KernelBench/level1/81_conv_transposed_2D_asymmetric_input_square_kernel___dilated____padded____strided__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/81_conv_transposed_2D_asymmetric_input_square_kernel___dilated____padded____strided__.py -------------------------------------------------------------------------------- /KernelBench/level1/82_conv_depthwise_2D_square_input_square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/82_conv_depthwise_2D_square_input_square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/83_conv_depthwise_2D_square_input_asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/83_conv_depthwise_2D_square_input_asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/84_conv_depthwise_2D_asymmetric_input_square_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/84_conv_depthwise_2D_asymmetric_input_square_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/85_conv_depthwise_2D_asymmetric_input_asymmetric_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/85_conv_depthwise_2D_asymmetric_input_asymmetric_kernel.py -------------------------------------------------------------------------------- /KernelBench/level1/86_conv_depthwise_separable_2D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/86_conv_depthwise_separable_2D.py -------------------------------------------------------------------------------- /KernelBench/level1/87_conv_pointwise_2D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/87_conv_pointwise_2D.py -------------------------------------------------------------------------------- /KernelBench/level1/88_MinGPTNewGelu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/88_MinGPTNewGelu.py -------------------------------------------------------------------------------- /KernelBench/level1/89_cumsum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/89_cumsum.py -------------------------------------------------------------------------------- /KernelBench/level1/8_Matmul_with_irregular_shapes_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/8_Matmul_with_irregular_shapes_.py -------------------------------------------------------------------------------- /KernelBench/level1/90_cumprod.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/90_cumprod.py -------------------------------------------------------------------------------- /KernelBench/level1/91_cumsum_reverse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/91_cumsum_reverse.py -------------------------------------------------------------------------------- /KernelBench/level1/92_cumsum_exclusive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/92_cumsum_exclusive.py -------------------------------------------------------------------------------- /KernelBench/level1/93_masked_cumsum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/93_masked_cumsum.py -------------------------------------------------------------------------------- /KernelBench/level1/94_MSELoss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/94_MSELoss.py -------------------------------------------------------------------------------- /KernelBench/level1/95_CrossEntropyLoss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/95_CrossEntropyLoss.py -------------------------------------------------------------------------------- /KernelBench/level1/96_HuberLoss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/96_HuberLoss.py -------------------------------------------------------------------------------- /KernelBench/level1/97_CosineSimilarityLoss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/97_CosineSimilarityLoss.py -------------------------------------------------------------------------------- /KernelBench/level1/98_KLDivLoss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/98_KLDivLoss.py -------------------------------------------------------------------------------- /KernelBench/level1/99_TripletMarginLoss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/99_TripletMarginLoss.py -------------------------------------------------------------------------------- /KernelBench/level1/9_Tall_skinny_matrix_multiplication_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level1/9_Tall_skinny_matrix_multiplication_.py -------------------------------------------------------------------------------- /KernelBench/level2/100_ConvTranspose3d_Clamp_Min_Divide.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/100_ConvTranspose3d_Clamp_Min_Divide.py -------------------------------------------------------------------------------- /KernelBench/level2/10_ConvTranspose2d_MaxPool_Hardtanh_Mean_Tanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/10_ConvTranspose2d_MaxPool_Hardtanh_Mean_Tanh.py -------------------------------------------------------------------------------- /KernelBench/level2/11_ConvTranspose2d_BatchNorm_Tanh_MaxPool_GroupNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/11_ConvTranspose2d_BatchNorm_Tanh_MaxPool_GroupNorm.py -------------------------------------------------------------------------------- /KernelBench/level2/12_Gemm_Multiply_LeakyReLU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/12_Gemm_Multiply_LeakyReLU.py -------------------------------------------------------------------------------- /KernelBench/level2/13_ConvTranspose3d_Mean_Add_Softmax_Tanh_Scaling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/13_ConvTranspose3d_Mean_Add_Softmax_Tanh_Scaling.py -------------------------------------------------------------------------------- /KernelBench/level2/14_Gemm_Divide_Sum_Scaling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/14_Gemm_Divide_Sum_Scaling.py -------------------------------------------------------------------------------- /KernelBench/level2/15_ConvTranspose3d_BatchNorm_Subtract.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/15_ConvTranspose3d_BatchNorm_Subtract.py -------------------------------------------------------------------------------- /KernelBench/level2/16_ConvTranspose2d_Mish_Add_Hardtanh_Scaling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/16_ConvTranspose2d_Mish_Add_Hardtanh_Scaling.py -------------------------------------------------------------------------------- /KernelBench/level2/17_Conv2d_InstanceNorm_Divide.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/17_Conv2d_InstanceNorm_Divide.py -------------------------------------------------------------------------------- /KernelBench/level2/18_Matmul_Sum_Max_AvgPool_LogSumExp_LogSumExp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/18_Matmul_Sum_Max_AvgPool_LogSumExp_LogSumExp.py -------------------------------------------------------------------------------- /KernelBench/level2/19_ConvTranspose2d_GELU_GroupNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/19_ConvTranspose2d_GELU_GroupNorm.py -------------------------------------------------------------------------------- /KernelBench/level2/1_Conv2D_ReLU_BiasAdd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/1_Conv2D_ReLU_BiasAdd.py -------------------------------------------------------------------------------- /KernelBench/level2/20_ConvTranspose3d_Sum_ResidualAdd_Multiply_ResidualAdd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/20_ConvTranspose3d_Sum_ResidualAdd_Multiply_ResidualAdd.py -------------------------------------------------------------------------------- /KernelBench/level2/21_Conv2d_Add_Scale_Sigmoid_GroupNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/21_Conv2d_Add_Scale_Sigmoid_GroupNorm.py -------------------------------------------------------------------------------- /KernelBench/level2/22_Matmul_Scale_ResidualAdd_Clamp_LogSumExp_Mish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/22_Matmul_Scale_ResidualAdd_Clamp_LogSumExp_Mish.py -------------------------------------------------------------------------------- /KernelBench/level2/23_Conv3d_GroupNorm_Mean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/23_Conv3d_GroupNorm_Mean.py -------------------------------------------------------------------------------- /KernelBench/level2/24_Conv3d_Min_Softmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/24_Conv3d_Min_Softmax.py -------------------------------------------------------------------------------- /KernelBench/level2/25_Conv2d_Min_Tanh_Tanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/25_Conv2d_Min_Tanh_Tanh.py -------------------------------------------------------------------------------- /KernelBench/level2/26_ConvTranspose3d_Add_HardSwish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/26_ConvTranspose3d_Add_HardSwish.py -------------------------------------------------------------------------------- /KernelBench/level2/27_Conv3d_HardSwish_ReLU_Softmax_Mean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/27_Conv3d_HardSwish_ReLU_Softmax_Mean.py -------------------------------------------------------------------------------- /KernelBench/level2/28_BMM_InstanceNorm_Sum_ResidualAdd_Multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/28_BMM_InstanceNorm_Sum_ResidualAdd_Multiply.py -------------------------------------------------------------------------------- /KernelBench/level2/29_Matmul_Mish_Mish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/29_Matmul_Mish_Mish.py -------------------------------------------------------------------------------- /KernelBench/level2/2_ConvTranspose2d_BiasAdd_Clamp_Scaling_Clamp_Divide.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/2_ConvTranspose2d_BiasAdd_Clamp_Scaling_Clamp_Divide.py -------------------------------------------------------------------------------- /KernelBench/level2/30_Gemm_GroupNorm_Hardtanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/30_Gemm_GroupNorm_Hardtanh.py -------------------------------------------------------------------------------- /KernelBench/level2/31_Conv2d_Min_Add_Multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/31_Conv2d_Min_Add_Multiply.py -------------------------------------------------------------------------------- /KernelBench/level2/32_Conv2d_Scaling_Min.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/32_Conv2d_Scaling_Min.py -------------------------------------------------------------------------------- /KernelBench/level2/33_Gemm_Scale_BatchNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/33_Gemm_Scale_BatchNorm.py -------------------------------------------------------------------------------- /KernelBench/level2/34_ConvTranspose3d_LayerNorm_GELU_Scaling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/34_ConvTranspose3d_LayerNorm_GELU_Scaling.py -------------------------------------------------------------------------------- /KernelBench/level2/35_Conv2d_Subtract_HardSwish_MaxPool_Mish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/35_Conv2d_Subtract_HardSwish_MaxPool_Mish.py -------------------------------------------------------------------------------- /KernelBench/level2/36_ConvTranspose2d_Min_Sum_GELU_Add.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/36_ConvTranspose2d_Min_Sum_GELU_Add.py -------------------------------------------------------------------------------- /KernelBench/level2/37_Matmul_Swish_Sum_GroupNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/37_Matmul_Swish_Sum_GroupNorm.py -------------------------------------------------------------------------------- /KernelBench/level2/38_ConvTranspose3d_AvgPool_Clamp_Softmax_Multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/38_ConvTranspose3d_AvgPool_Clamp_Softmax_Multiply.py -------------------------------------------------------------------------------- /KernelBench/level2/39_Gemm_Scale_BatchNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/39_Gemm_Scale_BatchNorm.py -------------------------------------------------------------------------------- /KernelBench/level2/3_ConvTranspose3d_Sum_LayerNorm_AvgPool_GELU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/3_ConvTranspose3d_Sum_LayerNorm_AvgPool_GELU.py -------------------------------------------------------------------------------- /KernelBench/level2/40_Matmul_Scaling_ResidualAdd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/40_Matmul_Scaling_ResidualAdd.py -------------------------------------------------------------------------------- /KernelBench/level2/41_Gemm_BatchNorm_GELU_GroupNorm_Mean_ReLU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/41_Gemm_BatchNorm_GELU_GroupNorm_Mean_ReLU.py -------------------------------------------------------------------------------- /KernelBench/level2/42_ConvTranspose2d_GlobalAvgPool_BiasAdd_LogSumExp_Sum_Multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/42_ConvTranspose2d_GlobalAvgPool_BiasAdd_LogSumExp_Sum_Multiply.py -------------------------------------------------------------------------------- /KernelBench/level2/43_Conv3d_Max_LogSumExp_ReLU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/43_Conv3d_Max_LogSumExp_ReLU.py -------------------------------------------------------------------------------- /KernelBench/level2/44_ConvTranspose2d_Multiply_GlobalAvgPool_GlobalAvgPool_Mean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/44_ConvTranspose2d_Multiply_GlobalAvgPool_GlobalAvgPool_Mean.py -------------------------------------------------------------------------------- /KernelBench/level2/45_Gemm_Sigmoid_Sum_LogSumExp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/45_Gemm_Sigmoid_Sum_LogSumExp.py -------------------------------------------------------------------------------- /KernelBench/level2/46_Conv2d_Subtract_Tanh_Subtract_AvgPool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/46_Conv2d_Subtract_Tanh_Subtract_AvgPool.py -------------------------------------------------------------------------------- /KernelBench/level2/47_Conv3d_Mish_Tanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/47_Conv3d_Mish_Tanh.py -------------------------------------------------------------------------------- /KernelBench/level2/48_Conv3d_Scaling_Tanh_Multiply_Sigmoid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/48_Conv3d_Scaling_Tanh_Multiply_Sigmoid.py -------------------------------------------------------------------------------- /KernelBench/level2/49_ConvTranspose3d_Softmax_Sigmoid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/49_ConvTranspose3d_Softmax_Sigmoid.py -------------------------------------------------------------------------------- /KernelBench/level2/4_Conv2d_Mish_Mish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/4_Conv2d_Mish_Mish.py -------------------------------------------------------------------------------- /KernelBench/level2/50_ConvTranspose3d_Scaling_AvgPool_BiasAdd_Scaling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/50_ConvTranspose3d_Scaling_AvgPool_BiasAdd_Scaling.py -------------------------------------------------------------------------------- /KernelBench/level2/51_Gemm_Subtract_GlobalAvgPool_LogSumExp_GELU_ResidualAdd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/51_Gemm_Subtract_GlobalAvgPool_LogSumExp_GELU_ResidualAdd.py -------------------------------------------------------------------------------- /KernelBench/level2/52_Conv2d_Activation_BatchNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/52_Conv2d_Activation_BatchNorm.py -------------------------------------------------------------------------------- /KernelBench/level2/53_Gemm_Scaling_Hardtanh_GELU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/53_Gemm_Scaling_Hardtanh_GELU.py -------------------------------------------------------------------------------- /KernelBench/level2/54_Conv2d_Multiply_LeakyReLU_GELU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/54_Conv2d_Multiply_LeakyReLU_GELU.py -------------------------------------------------------------------------------- /KernelBench/level2/55_Matmul_MaxPool_Sum_Scale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/55_Matmul_MaxPool_Sum_Scale.py -------------------------------------------------------------------------------- /KernelBench/level2/56_Matmul_Sigmoid_Sum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/56_Matmul_Sigmoid_Sum.py -------------------------------------------------------------------------------- /KernelBench/level2/57_Conv2d_ReLU_HardSwish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/57_Conv2d_ReLU_HardSwish.py -------------------------------------------------------------------------------- /KernelBench/level2/58_ConvTranspose3d_LogSumExp_HardSwish_Subtract_Clamp_Max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/58_ConvTranspose3d_LogSumExp_HardSwish_Subtract_Clamp_Max.py -------------------------------------------------------------------------------- /KernelBench/level2/59_Matmul_Swish_Scaling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/59_Matmul_Swish_Scaling.py -------------------------------------------------------------------------------- /KernelBench/level2/5_ConvTranspose2d_Subtract_Tanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/5_ConvTranspose2d_Subtract_Tanh.py -------------------------------------------------------------------------------- /KernelBench/level2/60_ConvTranspose3d_Swish_GroupNorm_HardSwish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/60_ConvTranspose3d_Swish_GroupNorm_HardSwish.py -------------------------------------------------------------------------------- /KernelBench/level2/61_ConvTranspose3d_ReLU_GroupNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/61_ConvTranspose3d_ReLU_GroupNorm.py -------------------------------------------------------------------------------- /KernelBench/level2/62_Matmul_GroupNorm_LeakyReLU_Sum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/62_Matmul_GroupNorm_LeakyReLU_Sum.py -------------------------------------------------------------------------------- /KernelBench/level2/63_Gemm_ReLU_Divide.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/63_Gemm_ReLU_Divide.py -------------------------------------------------------------------------------- /KernelBench/level2/64_Gemm_LogSumExp_LeakyReLU_LeakyReLU_GELU_GELU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/64_Gemm_LogSumExp_LeakyReLU_LeakyReLU_GELU_GELU.py -------------------------------------------------------------------------------- /KernelBench/level2/65_Conv2d_AvgPool_Sigmoid_Sum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/65_Conv2d_AvgPool_Sigmoid_Sum.py -------------------------------------------------------------------------------- /KernelBench/level2/66_Matmul_Dropout_Mean_Softmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/66_Matmul_Dropout_Mean_Softmax.py -------------------------------------------------------------------------------- /KernelBench/level2/67_Conv2d_GELU_GlobalAvgPool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/67_Conv2d_GELU_GlobalAvgPool.py -------------------------------------------------------------------------------- /KernelBench/level2/68_Matmul_Min_Subtract.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/68_Matmul_Min_Subtract.py -------------------------------------------------------------------------------- /KernelBench/level2/69_Conv2d_HardSwish_ReLU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/69_Conv2d_HardSwish_ReLU.py -------------------------------------------------------------------------------- /KernelBench/level2/6_Conv3d_Softmax_MaxPool_MaxPool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/6_Conv3d_Softmax_MaxPool_MaxPool.py -------------------------------------------------------------------------------- /KernelBench/level2/70_Gemm_Sigmoid_Scaling_ResidualAdd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/70_Gemm_Sigmoid_Scaling_ResidualAdd.py -------------------------------------------------------------------------------- /KernelBench/level2/71_Conv2d_Divide_LeakyReLU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/71_Conv2d_Divide_LeakyReLU.py -------------------------------------------------------------------------------- /KernelBench/level2/72_ConvTranspose3d_BatchNorm_AvgPool_AvgPool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/72_ConvTranspose3d_BatchNorm_AvgPool_AvgPool.py -------------------------------------------------------------------------------- /KernelBench/level2/73_Conv2d_BatchNorm_Scaling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/73_Conv2d_BatchNorm_Scaling.py -------------------------------------------------------------------------------- /KernelBench/level2/74_ConvTranspose3d_LeakyReLU_Multiply_LeakyReLU_Max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/74_ConvTranspose3d_LeakyReLU_Multiply_LeakyReLU_Max.py -------------------------------------------------------------------------------- /KernelBench/level2/75_Gemm_GroupNorm_Min_BiasAdd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/75_Gemm_GroupNorm_Min_BiasAdd.py -------------------------------------------------------------------------------- /KernelBench/level2/76_Gemm_Add_ReLU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/76_Gemm_Add_ReLU.py -------------------------------------------------------------------------------- /KernelBench/level2/77_ConvTranspose3d_Scale_BatchNorm_GlobalAvgPool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/77_ConvTranspose3d_Scale_BatchNorm_GlobalAvgPool.py -------------------------------------------------------------------------------- /KernelBench/level2/78_ConvTranspose3d_Max_Max_Sum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/78_ConvTranspose3d_Max_Max_Sum.py -------------------------------------------------------------------------------- /KernelBench/level2/79_Conv3d_Multiply_InstanceNorm_Clamp_Multiply_Max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/79_Conv3d_Multiply_InstanceNorm_Clamp_Multiply_Max.py -------------------------------------------------------------------------------- /KernelBench/level2/7_Conv3d_ReLU_LeakyReLU_GELU_Sigmoid_BiasAdd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/7_Conv3d_ReLU_LeakyReLU_GELU_Sigmoid_BiasAdd.py -------------------------------------------------------------------------------- /KernelBench/level2/80_Gemm_Max_Subtract_GELU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/80_Gemm_Max_Subtract_GELU.py -------------------------------------------------------------------------------- /KernelBench/level2/81_Gemm_Swish_Divide_Clamp_Tanh_Clamp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/81_Gemm_Swish_Divide_Clamp_Tanh_Clamp.py -------------------------------------------------------------------------------- /KernelBench/level2/82_Conv2d_Tanh_Scaling_BiasAdd_Max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/82_Conv2d_Tanh_Scaling_BiasAdd_Max.py -------------------------------------------------------------------------------- /KernelBench/level2/83_Conv3d_GroupNorm_Min_Clamp_Dropout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/83_Conv3d_GroupNorm_Min_Clamp_Dropout.py -------------------------------------------------------------------------------- /KernelBench/level2/84_Gemm_BatchNorm_Scaling_Softmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/84_Gemm_BatchNorm_Scaling_Softmax.py -------------------------------------------------------------------------------- /KernelBench/level2/85_Conv2d_GroupNorm_Scale_MaxPool_Clamp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/85_Conv2d_GroupNorm_Scale_MaxPool_Clamp.py -------------------------------------------------------------------------------- /KernelBench/level2/86_Matmul_Divide_GELU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/86_Matmul_Divide_GELU.py -------------------------------------------------------------------------------- /KernelBench/level2/87_Conv2d_Subtract_Subtract_Mish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/87_Conv2d_Subtract_Subtract_Mish.py -------------------------------------------------------------------------------- /KernelBench/level2/88_Gemm_GroupNorm_Swish_Multiply_Swish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/88_Gemm_GroupNorm_Swish_Multiply_Swish.py -------------------------------------------------------------------------------- /KernelBench/level2/89_ConvTranspose3d_MaxPool_Softmax_Subtract_Swish_Max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/89_ConvTranspose3d_MaxPool_Softmax_Subtract_Swish_Max.py -------------------------------------------------------------------------------- /KernelBench/level2/8_Conv3d_Divide_Max_GlobalAvgPool_BiasAdd_Sum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/8_Conv3d_Divide_Max_GlobalAvgPool_BiasAdd_Sum.py -------------------------------------------------------------------------------- /KernelBench/level2/90_Conv3d_LeakyReLU_Sum_Clamp_GELU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/90_Conv3d_LeakyReLU_Sum_Clamp_GELU.py -------------------------------------------------------------------------------- /KernelBench/level2/91_ConvTranspose2d_Softmax_BiasAdd_Scaling_Sigmoid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/91_ConvTranspose2d_Softmax_BiasAdd_Scaling_Sigmoid.py -------------------------------------------------------------------------------- /KernelBench/level2/92_Conv2d_GroupNorm_Tanh_HardSwish_ResidualAdd_LogSumExp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/92_Conv2d_GroupNorm_Tanh_HardSwish_ResidualAdd_LogSumExp.py -------------------------------------------------------------------------------- /KernelBench/level2/93_ConvTranspose2d_Add_Min_GELU_Multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/93_ConvTranspose2d_Add_Min_GELU_Multiply.py -------------------------------------------------------------------------------- /KernelBench/level2/94_Gemm_BiasAdd_Hardtanh_Mish_GroupNorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/94_Gemm_BiasAdd_Hardtanh_Mish_GroupNorm.py -------------------------------------------------------------------------------- /KernelBench/level2/95_Matmul_Add_Swish_Tanh_GELU_Hardtanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/95_Matmul_Add_Swish_Tanh_GELU_Hardtanh.py -------------------------------------------------------------------------------- /KernelBench/level2/96_ConvTranspose3d_Multiply_Max_GlobalAvgPool_Clamp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/96_ConvTranspose3d_Multiply_Max_GlobalAvgPool_Clamp.py -------------------------------------------------------------------------------- /KernelBench/level2/97_Matmul_BatchNorm_BiasAdd_Divide_Swish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/97_Matmul_BatchNorm_BiasAdd_Divide_Swish.py -------------------------------------------------------------------------------- /KernelBench/level2/98_Matmul_AvgPool_GELU_Scale_Max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/98_Matmul_AvgPool_GELU_Scale_Max.py -------------------------------------------------------------------------------- /KernelBench/level2/99_Matmul_GELU_Softmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/99_Matmul_GELU_Softmax.py -------------------------------------------------------------------------------- /KernelBench/level2/9_Matmul_Subtract_Multiply_ReLU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level2/9_Matmul_Subtract_Multiply_ReLU.py -------------------------------------------------------------------------------- /KernelBench/level3/10_ResNet101.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/10_ResNet101.py -------------------------------------------------------------------------------- /KernelBench/level3/11_VGG16.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/11_VGG16.py -------------------------------------------------------------------------------- /KernelBench/level3/12_VGG19.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/12_VGG19.py -------------------------------------------------------------------------------- /KernelBench/level3/13_DenseNet121TransitionLayer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/13_DenseNet121TransitionLayer.py -------------------------------------------------------------------------------- /KernelBench/level3/14_DenseNet121DenseBlock.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/14_DenseNet121DenseBlock.py -------------------------------------------------------------------------------- /KernelBench/level3/15_DenseNet121.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/15_DenseNet121.py -------------------------------------------------------------------------------- /KernelBench/level3/16_DenseNet201.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/16_DenseNet201.py -------------------------------------------------------------------------------- /KernelBench/level3/17_SqueezeNetFireModule.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/17_SqueezeNetFireModule.py -------------------------------------------------------------------------------- /KernelBench/level3/18_SqueezeNet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/18_SqueezeNet.py -------------------------------------------------------------------------------- /KernelBench/level3/19_MobileNetV1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/19_MobileNetV1.py -------------------------------------------------------------------------------- /KernelBench/level3/1_MLP.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/1_MLP.py -------------------------------------------------------------------------------- /KernelBench/level3/20_MobileNetV2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/20_MobileNetV2.py -------------------------------------------------------------------------------- /KernelBench/level3/21_EfficientNetMBConv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/21_EfficientNetMBConv.py -------------------------------------------------------------------------------- /KernelBench/level3/22_EfficientNetB0.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/22_EfficientNetB0.py -------------------------------------------------------------------------------- /KernelBench/level3/23_EfficientNetB1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/23_EfficientNetB1.py -------------------------------------------------------------------------------- /KernelBench/level3/24_EfficientNetB2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/24_EfficientNetB2.py -------------------------------------------------------------------------------- /KernelBench/level3/25_ShuffleNetUnit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/25_ShuffleNetUnit.py -------------------------------------------------------------------------------- /KernelBench/level3/26_ShuffleNet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/26_ShuffleNet.py -------------------------------------------------------------------------------- /KernelBench/level3/27_RegNet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/27_RegNet.py -------------------------------------------------------------------------------- /KernelBench/level3/28_VisionTransformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/28_VisionTransformer.py -------------------------------------------------------------------------------- /KernelBench/level3/29_SwinMLP.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/29_SwinMLP.py -------------------------------------------------------------------------------- /KernelBench/level3/2_ShallowWideMLP.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/2_ShallowWideMLP.py -------------------------------------------------------------------------------- /KernelBench/level3/30_SwinTransformerV2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/30_SwinTransformerV2.py -------------------------------------------------------------------------------- /KernelBench/level3/31_VisionAttention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/31_VisionAttention.py -------------------------------------------------------------------------------- /KernelBench/level3/32_ConvolutionalVisionTransformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/32_ConvolutionalVisionTransformer.py -------------------------------------------------------------------------------- /KernelBench/level3/33_VanillaRNN.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/33_VanillaRNN.py -------------------------------------------------------------------------------- /KernelBench/level3/34_VanillaRNNHidden.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/34_VanillaRNNHidden.py -------------------------------------------------------------------------------- /KernelBench/level3/35_LTSM.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/35_LTSM.py -------------------------------------------------------------------------------- /KernelBench/level3/36_LTSMHn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/36_LTSMHn.py -------------------------------------------------------------------------------- /KernelBench/level3/37_LTSMCn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/37_LTSMCn.py -------------------------------------------------------------------------------- /KernelBench/level3/38_LTSMBidirectional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/38_LTSMBidirectional.py -------------------------------------------------------------------------------- /KernelBench/level3/39_GRU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/39_GRU.py -------------------------------------------------------------------------------- /KernelBench/level3/3_DeepNarrowMLP.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/3_DeepNarrowMLP.py -------------------------------------------------------------------------------- /KernelBench/level3/40_GRUHidden.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/40_GRUHidden.py -------------------------------------------------------------------------------- /KernelBench/level3/41_GRUBirectional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/41_GRUBirectional.py -------------------------------------------------------------------------------- /KernelBench/level3/42_GRUBidirectionalHidden.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/42_GRUBidirectionalHidden.py -------------------------------------------------------------------------------- /KernelBench/level3/43_MinGPTCausalAttention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/43_MinGPTCausalAttention.py -------------------------------------------------------------------------------- /KernelBench/level3/44_MiniGPTBlock.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/44_MiniGPTBlock.py -------------------------------------------------------------------------------- /KernelBench/level3/45_UNetSoftmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/45_UNetSoftmax.py -------------------------------------------------------------------------------- /KernelBench/level3/46_NetVladWithGhostClusters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/46_NetVladWithGhostClusters.py -------------------------------------------------------------------------------- /KernelBench/level3/47_NetVladNoGhostClusters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/47_NetVladNoGhostClusters.py -------------------------------------------------------------------------------- /KernelBench/level3/48_Mamba2ReturnY.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/48_Mamba2ReturnY.py -------------------------------------------------------------------------------- /KernelBench/level3/49_Mamba2ReturnFinalState.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/49_Mamba2ReturnFinalState.py -------------------------------------------------------------------------------- /KernelBench/level3/4_LeNet5.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/4_LeNet5.py -------------------------------------------------------------------------------- /KernelBench/level3/50_ReLUSelfAttention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/50_ReLUSelfAttention.py -------------------------------------------------------------------------------- /KernelBench/level3/5_AlexNet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/5_AlexNet.py -------------------------------------------------------------------------------- /KernelBench/level3/6_GoogleNetInceptionModule.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/6_GoogleNetInceptionModule.py -------------------------------------------------------------------------------- /KernelBench/level3/7_GoogleNetInceptionV1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/7_GoogleNetInceptionV1.py -------------------------------------------------------------------------------- /KernelBench/level3/8_ResNetBasicBlock.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/8_ResNetBasicBlock.py -------------------------------------------------------------------------------- /KernelBench/level3/9_ResNet18.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level3/9_ResNet18.py -------------------------------------------------------------------------------- /KernelBench/level4/10_google-bigbird-roberta-base_bs1024_seq32.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/10_google-bigbird-roberta-base_bs1024_seq32.py -------------------------------------------------------------------------------- /KernelBench/level4/11_google-electra-small-discriminator_bs1_seq511.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/11_google-electra-small-discriminator_bs1_seq511.py -------------------------------------------------------------------------------- /KernelBench/level4/12_google-electra-small-discriminator_bs1024_seq32.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/12_google-electra-small-discriminator_bs1024_seq32.py -------------------------------------------------------------------------------- /KernelBench/level4/13_google-reformer-enwik8_bs32_seq256.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/13_google-reformer-enwik8_bs32_seq256.py -------------------------------------------------------------------------------- /KernelBench/level4/14_google-electra-small-discriminator_bs32_seq256.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/14_google-electra-small-discriminator_bs32_seq256.py -------------------------------------------------------------------------------- /KernelBench/level4/15_google-reformer-enwik8_bs1024_seq32.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/15_google-reformer-enwik8_bs1024_seq32.py -------------------------------------------------------------------------------- /KernelBench/level4/16_gpt2_bs1_seq1023.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/16_gpt2_bs1_seq1023.py -------------------------------------------------------------------------------- /KernelBench/level4/17_facebook-bart-large_bs1024_seq32.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/17_facebook-bart-large_bs1024_seq32.py -------------------------------------------------------------------------------- /KernelBench/level4/18_EleutherAI-gpt-neo-2p7B_bs512_seq32.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/18_EleutherAI-gpt-neo-2p7B_bs512_seq32.py -------------------------------------------------------------------------------- /KernelBench/level4/19_gpt2_bs1024_seq32.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/19_gpt2_bs1024_seq32.py -------------------------------------------------------------------------------- /KernelBench/level4/1_EleutherAI-gpt-neo-2p7B_bs32_seq256.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/1_EleutherAI-gpt-neo-2p7B_bs32_seq256.py -------------------------------------------------------------------------------- /KernelBench/level4/20_facebook-bart-large_bs32_seq256.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/20_facebook-bart-large_bs32_seq256.py -------------------------------------------------------------------------------- /KernelBench/level4/2_facebook-opt-1p3b_bs1_seq2047.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/2_facebook-opt-1p3b_bs1_seq2047.py -------------------------------------------------------------------------------- /KernelBench/level4/3_EleutherAI-gpt-neo-2p7B_bs1_seq2047.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/3_EleutherAI-gpt-neo-2p7B_bs1_seq2047.py -------------------------------------------------------------------------------- /KernelBench/level4/4_facebook-opt-1p3b_bs32_seq256.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/4_facebook-opt-1p3b_bs32_seq256.py -------------------------------------------------------------------------------- /KernelBench/level4/5_google-bigbird-roberta-base_bs1_seq4095.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/5_google-bigbird-roberta-base_bs1_seq4095.py -------------------------------------------------------------------------------- /KernelBench/level4/6_facebook-bart-large_bs1_seq1023.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/6_facebook-bart-large_bs1_seq1023.py -------------------------------------------------------------------------------- /KernelBench/level4/7_gpt2_bs32_seq256.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/7_gpt2_bs32_seq256.py -------------------------------------------------------------------------------- /KernelBench/level4/8_facebook-opt-1p3b_bs512_seq32.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/8_facebook-opt-1p3b_bs512_seq32.py -------------------------------------------------------------------------------- /KernelBench/level4/9_google-bigbird-roberta-base_bs32_seq256.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/KernelBench/level4/9_google-bigbird-roberta-base_bs32_seq256.py -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/README.md -------------------------------------------------------------------------------- /TRITON_INTEGRATION_GUIDE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/TRITON_INTEGRATION_GUIDE.md -------------------------------------------------------------------------------- /TRITON_README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/TRITON_README.md -------------------------------------------------------------------------------- /assets/figures/KernelBenchMascot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/assets/figures/KernelBenchMascot.png -------------------------------------------------------------------------------- /assets/figures/KernelBenchWorkFlow.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/assets/figures/KernelBenchWorkFlow.png -------------------------------------------------------------------------------- /cursorchanges.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/cursorchanges.md -------------------------------------------------------------------------------- /docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/docker-compose.yml -------------------------------------------------------------------------------- /eval_py.diff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/eval_py.diff -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/requirements.txt -------------------------------------------------------------------------------- /results/timing/A100-80GB_modal/baseline_time_torch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/A100-80GB_modal/baseline_time_torch.json -------------------------------------------------------------------------------- /results/timing/A100-80GB_modal/baseline_time_torch_compile_inductor_default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/A100-80GB_modal/baseline_time_torch_compile_inductor_default.json -------------------------------------------------------------------------------- /results/timing/A100_modal/baseline_time_torch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/A100_modal/baseline_time_torch.json -------------------------------------------------------------------------------- /results/timing/A100_modal/baseline_time_torch_compile_inductor_default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/A100_modal/baseline_time_torch_compile_inductor_default.json -------------------------------------------------------------------------------- /results/timing/A10G_modal/baseline_time_torch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/A10G_modal/baseline_time_torch.json -------------------------------------------------------------------------------- /results/timing/A10G_modal/baseline_time_torch_compile_inductor_default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/A10G_modal/baseline_time_torch_compile_inductor_default.json -------------------------------------------------------------------------------- /results/timing/B200_together/baseline_time_torch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/B200_together/baseline_time_torch.json -------------------------------------------------------------------------------- /results/timing/B200_together/baseline_time_torch_compile_cudagraphs.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/B200_together/baseline_time_torch_compile_cudagraphs.json -------------------------------------------------------------------------------- /results/timing/B200_together/baseline_time_torch_compile_inductor_default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/B200_together/baseline_time_torch_compile_inductor_default.json -------------------------------------------------------------------------------- /results/timing/B200_together/baseline_time_torch_compile_inductor_max-autotune-no-cudagraphs.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/B200_together/baseline_time_torch_compile_inductor_max-autotune-no-cudagraphs.json -------------------------------------------------------------------------------- /results/timing/B200_together/baseline_time_torch_compile_inductor_max-autotune.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/B200_together/baseline_time_torch_compile_inductor_max-autotune.json -------------------------------------------------------------------------------- /results/timing/B200_together/baseline_time_torch_compile_inductor_reduce-overhead.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/B200_together/baseline_time_torch_compile_inductor_reduce-overhead.json -------------------------------------------------------------------------------- /results/timing/H100_together/baseline_time_torch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/H100_together/baseline_time_torch.json -------------------------------------------------------------------------------- /results/timing/H100_together/baseline_time_torch_compile_cudagraphs.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/H100_together/baseline_time_torch_compile_cudagraphs.json -------------------------------------------------------------------------------- /results/timing/H100_together/baseline_time_torch_compile_inductor_default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/H100_together/baseline_time_torch_compile_inductor_default.json -------------------------------------------------------------------------------- /results/timing/H100_together/baseline_time_torch_compile_inductor_max-autotune-no-cudagraphs.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/H100_together/baseline_time_torch_compile_inductor_max-autotune-no-cudagraphs.json -------------------------------------------------------------------------------- /results/timing/H100_together/baseline_time_torch_compile_inductor_max-autotune.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/H100_together/baseline_time_torch_compile_inductor_max-autotune.json -------------------------------------------------------------------------------- /results/timing/H100_together/baseline_time_torch_compile_inductor_reduce-overhead.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/H100_together/baseline_time_torch_compile_inductor_reduce-overhead.json -------------------------------------------------------------------------------- /results/timing/L40S_matx3/baseline_time_torch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L40S_matx3/baseline_time_torch.json -------------------------------------------------------------------------------- /results/timing/L40S_matx3/baseline_time_torch_compile_cudagraphs.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L40S_matx3/baseline_time_torch_compile_cudagraphs.json -------------------------------------------------------------------------------- /results/timing/L40S_matx3/baseline_time_torch_compile_inductor_default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L40S_matx3/baseline_time_torch_compile_inductor_default.json -------------------------------------------------------------------------------- /results/timing/L40S_matx3/baseline_time_torch_compile_inductor_max-autotune-no-cudagraphs.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L40S_matx3/baseline_time_torch_compile_inductor_max-autotune-no-cudagraphs.json -------------------------------------------------------------------------------- /results/timing/L40S_matx3/baseline_time_torch_compile_inductor_max-autotune.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L40S_matx3/baseline_time_torch_compile_inductor_max-autotune.json -------------------------------------------------------------------------------- /results/timing/L40S_matx3/baseline_time_torch_compile_inductor_reduce-overhead.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L40S_matx3/baseline_time_torch_compile_inductor_reduce-overhead.json -------------------------------------------------------------------------------- /results/timing/L40S_modal/baseline_time_torch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L40S_modal/baseline_time_torch.json -------------------------------------------------------------------------------- /results/timing/L40S_modal/baseline_time_torch_compile_inductor_default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L40S_modal/baseline_time_torch_compile_inductor_default.json -------------------------------------------------------------------------------- /results/timing/L4_modal/baseline_time_torch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L4_modal/baseline_time_torch.json -------------------------------------------------------------------------------- /results/timing/L4_modal/baseline_time_torch_compile_inductor_default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/L4_modal/baseline_time_torch_compile_inductor_default.json -------------------------------------------------------------------------------- /results/timing/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/README.md -------------------------------------------------------------------------------- /results/timing/T4_modal/baseline_time_torch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/T4_modal/baseline_time_torch.json -------------------------------------------------------------------------------- /results/timing/T4_modal/baseline_time_torch_compile_inductor_default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/T4_modal/baseline_time_torch_compile_inductor_default.json -------------------------------------------------------------------------------- /results/timing/old/baseline_time_cleaned.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/old/baseline_time_cleaned.json -------------------------------------------------------------------------------- /results/timing/old/baseline_time_matx2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/old/baseline_time_matx2.json -------------------------------------------------------------------------------- /results/timing/old/baseline_time_matx3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/old/baseline_time_matx3.json -------------------------------------------------------------------------------- /results/timing/old/baseline_time_torch_compile_cleaned.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/old/baseline_time_torch_compile_cleaned.json -------------------------------------------------------------------------------- /results/timing/old/baseline_time_torch_compile_matx2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/old/baseline_time_torch_compile_matx2.json -------------------------------------------------------------------------------- /results/timing/old/baseline_time_torch_compile_matx3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/results/timing/old/baseline_time_torch_compile_matx3.json -------------------------------------------------------------------------------- /run_and_check_triton_py.diff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/run_and_check_triton_py.diff -------------------------------------------------------------------------------- /scripts/benchmark_eval_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/benchmark_eval_analysis.py -------------------------------------------------------------------------------- /scripts/debug_stddout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/debug_stddout.py -------------------------------------------------------------------------------- /scripts/eval_from_generations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/eval_from_generations.py -------------------------------------------------------------------------------- /scripts/generate_and_eval_single_sample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/generate_and_eval_single_sample.py -------------------------------------------------------------------------------- /scripts/generate_and_eval_single_sample_modal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/generate_and_eval_single_sample_modal.py -------------------------------------------------------------------------------- /scripts/generate_baseline_time.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/generate_baseline_time.py -------------------------------------------------------------------------------- /scripts/generate_baseline_time_modal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/generate_baseline_time_modal.py -------------------------------------------------------------------------------- /scripts/generate_samples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/generate_samples.py -------------------------------------------------------------------------------- /scripts/inspect_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/inspect_baseline.py -------------------------------------------------------------------------------- /scripts/inspect_kernel_pytorch_profiler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/inspect_kernel_pytorch_profiler.py -------------------------------------------------------------------------------- /scripts/inspect_triton.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/inspect_triton.py -------------------------------------------------------------------------------- /scripts/run_and_check.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/run_and_check.py -------------------------------------------------------------------------------- /scripts/run_and_check_triton.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/run_and_check_triton.py -------------------------------------------------------------------------------- /scripts/verify_bench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/verify_bench.py -------------------------------------------------------------------------------- /scripts/verify_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/scripts/verify_generation.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/setup.py -------------------------------------------------------------------------------- /src/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/analysis.py -------------------------------------------------------------------------------- /src/compile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/compile.py -------------------------------------------------------------------------------- /src/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/dataset.py -------------------------------------------------------------------------------- /src/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/eval.py -------------------------------------------------------------------------------- /src/frameworks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/frameworks.py -------------------------------------------------------------------------------- /src/make_hf_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/make_hf_dataset.py -------------------------------------------------------------------------------- /src/prompt_constructor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompt_constructor.py -------------------------------------------------------------------------------- /src/prompts/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/README.md -------------------------------------------------------------------------------- /src/prompts/cot/model_cot_fuse_gelu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/cot/model_cot_fuse_gelu.py -------------------------------------------------------------------------------- /src/prompts/cot/model_cot_mnist2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/cot/model_cot_mnist2.py -------------------------------------------------------------------------------- /src/prompts/cot/model_cot_tiled_matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/cot/model_cot_tiled_matmul.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_ex_add.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_ex_add.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_ex_flash_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_ex_flash_attn.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_ex_fuse_gelu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_ex_fuse_gelu.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_ex_mnist2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_ex_mnist2.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_ex_tiled_matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_ex_tiled_matmul.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_new_ex_add.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_new_ex_add.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_new_ex_flash_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_new_ex_flash_attn.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_new_ex_fuse_gelu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_new_ex_fuse_gelu.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_new_ex_mnist2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_new_ex_mnist2.py -------------------------------------------------------------------------------- /src/prompts/few_shot/model_new_ex_tiled_matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/few_shot/model_new_ex_tiled_matmul.py -------------------------------------------------------------------------------- /src/prompts/hardware/gpu_specs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/hardware/gpu_specs.py -------------------------------------------------------------------------------- /src/prompts/model_ex_0.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/prompts/model_ex_1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/model_ex_1.py -------------------------------------------------------------------------------- /src/prompts/model_ex_2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/model_ex_2.py -------------------------------------------------------------------------------- /src/prompts/model_ex_add.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/model_ex_add.py -------------------------------------------------------------------------------- /src/prompts/model_new_ex_0.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/prompts/model_new_ex_1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/model_new_ex_1.py -------------------------------------------------------------------------------- /src/prompts/model_new_ex_2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/model_new_ex_2.py -------------------------------------------------------------------------------- /src/prompts/model_new_ex_add.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/model_new_ex_add.py -------------------------------------------------------------------------------- /src/prompts/model_new_ex_add_triton.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/model_new_ex_add_triton.py -------------------------------------------------------------------------------- /src/prompts/model_new_ex_matmul_triton.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/prompts/model_new_ex_matmul_triton.py -------------------------------------------------------------------------------- /src/score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/score.py -------------------------------------------------------------------------------- /src/scratch/log.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/scratch/log.txt -------------------------------------------------------------------------------- /src/scratch/model.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/scratch/model_new.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/scratch/prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/scratch/prompt.txt -------------------------------------------------------------------------------- /src/scratch/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/scratch/test.py -------------------------------------------------------------------------------- /src/unit_tests/test_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/unit_tests/test_dataset.py -------------------------------------------------------------------------------- /src/unit_tests/test_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/unit_tests/test_score.py -------------------------------------------------------------------------------- /src/unit_tests/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/unit_tests/test_utils.py -------------------------------------------------------------------------------- /src/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/src/utils.py -------------------------------------------------------------------------------- /test_setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/test_setup.py -------------------------------------------------------------------------------- /test_triton_integration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/test_triton_integration.py -------------------------------------------------------------------------------- /triton_standard_matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/triton_standard_matmul.py -------------------------------------------------------------------------------- /triton_test/triton_alexnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/triton_test/triton_alexnet.py -------------------------------------------------------------------------------- /triton_test/triton_gpt2_passthrough.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/triton_test/triton_gpt2_passthrough.py -------------------------------------------------------------------------------- /triton_test/triton_matmul_gelu_softmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/triton_test/triton_matmul_gelu_softmax.py -------------------------------------------------------------------------------- /triton_test/triton_mingpt_causal_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/triton_test/triton_mingpt_causal_attention.py -------------------------------------------------------------------------------- /triton_test/triton_relu_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lossfunk/KernelBench-v2/HEAD/triton_test/triton_relu_kernel.py --------------------------------------------------------------------------------