apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Optimize]support machete weight only gemm (#3561)

Browse Source 
* support machete weight only gemm

* add generate

* update

* fix

* change file location

* add sm_version limit

* fix

* fix

* fix ci

* fix coverage

* fix xpu
This commit is contained in:
Sunny-bot1
2025-08-28 09:49:58 +08:00
committed by GitHub
parent e37e86b3b8
commit 479c8b85d3
29 changed files with 5436 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
custom_ops/setup_ops.py
View File

@@ -512,6 +512,8 @@ elif paddle.is_compiled_with_cuda():
sources += find_end_files("gpu_ops/w4afp8_gemm", ".cu")
os.system("python utils/auto_gen_wfp8afp8_sparse_gemm_kernel.py")
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")
setup(
name="fastdeploy_ops",