apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 00:33:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

support w4afp8 EP inference (#3044)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Yuan Xiaolan
2025-08-25 11:27:45 +08:00
committed by GitHub
parent 46664985fc
commit 9205c88da1
17 changed files with 995 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
fastdeploy/model_executor/layers/moe/ep.py
View File

@@ -389,7 +389,7 @@ class EPPrefillRunner(EPRunner):
):
(
num_tokens_per_rank,
_,
num_tokens_per_rdma_rank,
num_tokens_per_expert,
is_token_in_rank,
_,
@@ -399,6 +399,7 @@ class EPPrefillRunner(EPRunner):
dispatch_args = {
"x": (x, x_scale_tensor) if x_scale_tensor is not None else x,
"num_tokens_per_rank": num_tokens_per_rank,
"num_tokens_per_rdma_rank": num_tokens_per_rdma_rank,
"is_token_in_rank": is_token_in_rank,
"num_tokens_per_expert": num_tokens_per_expert,
"config": self.ep_engine.ep_config,