apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-24 17:49:42 +08:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity

[BugFix] Fix model loading error for 300B FP8 EP parallel test case (#6382) (#6436)

Browse Source 
* fix fp8 bug

* fix

* fix comment, cn to en

* fix ci

* del else in utils

* fix review

Co-authored-by: yuxuan <157974576+Echo-Nie@users.noreply.github.com>
This commit is contained in:
JYChen
2026-02-10 20:53:47 +08:00
committed by GitHub
parent c53c34ddc0
commit 1efa37a681
3 changed files with 3 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/model_executor/model_loader/default_loader_v1.py
+1 -1
View File
@@ -58,7 +58,7 @@ class DefaultModelLoaderV1(BaseModelLoader):
load_weights_from_cache(model, weights_iterator)
else:
model.load_weights(weights_iterator)
# Execute post-processing after weight loading
process_final_after_loading(model, fd_config)
self.clean_memory_fragments()