apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Revert "[Feature] block sparse attention (#3209)" (#3647)

Browse Source 
This reverts commit 646a0c2fd8.
This commit is contained in:
Jiang-Jia-Jun
2025-08-27 17:35:04 +08:00
committed by GitHub
parent b2afdf4fc6
commit c694fa2879
31 changed files with 10 additions and 6507 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
custom_ops/setup_ops.py
View File

@@ -385,7 +385,6 @@ elif paddle.is_compiled_with_cuda():
"-Igpu_ops",
"-Ithird_party/nlohmann_json/include",
]
nvcc_version = get_nvcc_version()
print(f"nvcc_version = {nvcc_version}")
if nvcc_version >= 12.0:
@@ -509,10 +508,6 @@ elif paddle.is_compiled_with_cuda():
# Hopper optmized mla
sources += find_end_files("gpu_ops/mla_attn", ".cu")
sources += ["gpu_ops/flash_mask_attn/flash_mask_attn.cu"]
sources += find_end_files("gpu_ops/moba_attn/moba_decoder_attn/", ".cu")
sources += find_end_files("gpu_ops/moba_attn/moba_encoder_attn/", ".cu")
sources += find_end_files("gpu_ops/moba_attn/moba_process/", ".cu")
sources += ["gpu_ops/moba_attn/moba_attn.cu"]
os.system("python utils/auto_gen_w4afp8_gemm_kernel.py")
sources += find_end_files("gpu_ops/w4afp8_gemm", ".cu")
os.system("python utils/auto_gen_wfp8afp8_sparse_gemm_kernel.py")