apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 09:07:10 +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
tests/model_loader/test_common_model.py
View File

@@ -174,7 +174,7 @@ model_param_map = {
{
"quant_type": "block_wise_fp8",
"backend": "triton",
"env": {"FD_USE_DEEP_GEMM": "0", "DG_NVCC_OVERRIDE_CPP_STANDARD": "17"},
"env": {"DG_NVCC_OVERRIDE_CPP_STANDARD": "17"},
},
{"quant_type": "block_wise_fp8", "backend": "deepgemm", "env": {"DG_NVCC_OVERRIDE_CPP_STANDARD": "17"}},
],