apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 00:06:38 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[FIX]Fix Machete compile via ENABLE_MACHETE (#3727)

Browse Source 
* add ENABLE_MACHETE

* fix

* revert

* update

* pre_commit

* fix

* fix

---------

Co-authored-by: Ayakouji <yuhongh@qq.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: aquagull <hongyuh@qq.com>
This commit is contained in:
Sunny-bot1
2025-08-30 17:50:17 +08:00
committed by GitHub
parent b9af95cf1c
commit fe5d09f9ee
4 changed files with 17 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
custom_ops/setup_ops.py
View File

@@ -373,6 +373,7 @@ elif paddle.is_compiled_with_cuda():
if not os.listdir(json_dir):
raise ValueError("Git clone nlohmann_json failed!")
cc_compile_args = []
nvcc_compile_args = get_gencode_flags(archs)
nvcc_compile_args += ["-DPADDLE_DEV"]
nvcc_compile_args += ["-DPADDLE_ON_INFERENCE"]
@@ -519,12 +520,13 @@ elif paddle.is_compiled_with_cuda():
sources += find_end_files("gpu_ops/wfp8afp8_sparse_gemm", ".cu")
os.system("python gpu_ops/machete/generate.py")
sources += find_end_files("gpu_ops/machete", ".cu")
cc_compile_args += ["-DENABLE_MACHETE"]
setup(
name="fastdeploy_ops",
ext_modules=CUDAExtension(
sources=sources,
extra_compile_args={"nvcc": nvcc_compile_args},
extra_compile_args={"cxx": cc_compile_args, "nvcc": nvcc_compile_args},
libraries=["cublasLt"],
extra_link_args=["-lcuda"],
),