avo_test_cases / flashmla_tests

567 kB

Ctrl+K

1 contributor

History: 1 commit

jiliu1

Upload folder using huggingface_hub

4118053 verified 4 months ago

__pycache__
Upload folder using huggingface_hub 4 months ago
build
Upload folder using huggingface_hub 4 months ago
kernelkit
Upload folder using huggingface_hub 4 months ago
lib.py

16.8 kB
Upload folder using huggingface_hub 4 months ago
quant.py

8.16 kB
Upload folder using huggingface_hub 4 months ago
ref.py

4.56 kB
Upload folder using huggingface_hub 4 months ago
test_flash_mla_dense_decoding.py

9.05 kB
Upload folder using huggingface_hub 4 months ago
test_flash_mla_sparse_decoding.py

12.7 kB
Upload folder using huggingface_hub 4 months ago
test_flash_mla_sparse_decoding_triton_geak_correctness.py

6.62 kB
Upload folder using huggingface_hub 4 months ago
test_flash_mla_sparse_decoding_triton_geak_perf.py

4.59 kB
Upload folder using huggingface_hub 4 months ago
test_flash_mla_sparse_decoding_triton_v1.py

12.8 kB
Upload folder using huggingface_hub 4 months ago
test_flash_mla_sparse_prefill.py

6.35 kB
Upload folder using huggingface_hub 4 months ago
test_flash_mla_sparse_prefill_triton_geak_correctness.py

5.63 kB
Upload folder using huggingface_hub 4 months ago
test_flash_mla_sparse_prefill_triton_geak_perf.py

4.41 kB
Upload folder using huggingface_hub 4 months ago
test_flash_mla_sparse_prefill_triton_v1.py

6.72 kB
Upload folder using huggingface_hub 4 months ago
test_fmha_sm100.py

7.55 kB
Upload folder using huggingface_hub 4 months ago
triton_mla_kernels.py

5.39 kB
Upload folder using huggingface_hub 4 months ago
triton_mla_kernels_decode_common.py

18.7 kB
Upload folder using huggingface_hub 4 months ago
triton_mla_kernels_decode_fused.py

94.8 kB
Upload folder using huggingface_hub 4 months ago
triton_mla_kernels_decode_model1.py

46.3 kB
Upload folder using huggingface_hub 4 months ago
triton_mla_kernels_decode_optimized.py

9.3 kB
Upload folder using huggingface_hub 4 months ago
triton_mla_kernels_decode_splitk.py

18.5 kB
Upload folder using huggingface_hub 4 months ago
triton_mla_kernels_decode_v32.py

50.3 kB
Upload folder using huggingface_hub 4 months ago
triton_mla_kernels_decode_v32_fused.py

16.1 kB
Upload folder using huggingface_hub 4 months ago
triton_mla_kernels_prefill_optimized.py

16.6 kB
Upload folder using huggingface_hub 4 months ago