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

MoE Default use triton's blockwise fp8 in TP Case (#3678)

Browse Source
This commit is contained in:
周周周
2025-08-29 11:07:30 +08:00
committed by GitHub
parent b6edd15d55
commit 17b414c2df
7 changed files with 5 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/usage/environment_variables.md
View File

@@ -70,7 +70,7 @@ environment_variables: dict[str, Callable[[], Any]] = {
# Whether to use DeepGemm for FP8 blockwise MoE.
"FD_USE_DEEP_GEMM":
lambda: bool(int(os.getenv("FD_USE_DEEP_GEMM", "1"))),
lambda: bool(int(os.getenv("FD_USE_DEEP_GEMM", "0"))),
}
```