auto-round
[risky]reduce ram usage of loading moe without monkey patch and fix qwen3-flash-next group_size issue
#2291
Merged
Merged
[risky]reduce ram usage of loading moe without monkey patch and fix qwen3-flash-next group_size issue #2291
wenhuach21
merged
27 commits into
main
from
fix_moe_loading
update
5fe714d6
![pre-commit-ci[bot]](https://avatars.githubusercontent.com/in/68672?v=4&s=60)
[pre-commit.ci] auto fixes from pre-commit.com hooks
b0556ad4
update
9f9331c3
update
f644f237
Merge branch 'main' into fix_moe_loading
fd6f5f04
[pre-commit.ci] auto fixes from pre-commit.com hooks
c0b2cee2
disable all moe replacements
84fe3554
Merge branch 'fix_moe_loading' of https://github.com/intel/auto-round…
481f1a3f
wenhuach21
changed the title 
fix moe gguf
eb6cb5d5
wenhuach21
commented
on 2026-09-04
fix: restore dedicated MoE replacements
5f37b278
Merge branch 'main' into fix_moe_loading
853aa506
try to fix ut
5fd7c8f5
Merge branch 'fix_moe_loading' of https://github.com/intel/auto-round…
a91c2dc0
Merge branch 'main' into fix_moe_loading
b697e4d4
try to fix glm5.3
c309d2a9
update
cdca4cf7
fix qwen3.8-flash-next issue
bf1a833f
[pre-commit.ci] auto fixes from pre-commit.com hooks
1cd87ea8
wenhuach21
changed the title
wenhuach21
changed the title
luoyu-intel
approved these changes
on 2026-09-04
try to fix ut
8a96a36a
Merge branch 'fix_moe_loading' of https://github.com/intel/auto-round…
cc2cb6ad
[pre-commit.ci] auto fixes from pre-commit.com hooks
b55f562a
try to fix ut
2b0530b9
Merge branch 'fix_moe_loading' of https://github.com/intel/auto-round…
aef03745
[pre-commit.ci] auto fixes from pre-commit.com hooks
cc3aa366
refine
9b7b572b
Merge branch 'fix_moe_loading' of https://github.com/intel/auto-round…
b3df3b55
fix ut
5f2eeea3
Assignees
No one assigned
Labels
ready
Milestone
No milestone
Login to write a write a comment.
Login via GitHub