Support mxfp nvfp lmhead quant #1051
WeiweiZhang1
merged
24 commits into
main
from
support_mxfp_nvfp_lmhead_quant
fp8 exporting bugfix
719e5abb
Merge branch 'main' of https://github.com/intel/auto-round into main
8e8b04f6
Merge branch 'main' of https://github.com/intel/auto-round into main
57842a16
refine exllama backend cuda UT
c2daa790
Merge branch 'main' of https://github.com/intel/auto-round into main
ca36a70e
Merge branch 'main' of https://github.com/intel/auto-round into main
9ab08431
add lm_head layer act_max hook, enable mxfp/nvfp lm_head export
8176d2ed
![pre-commit-ci[bot]](https://avatars.githubusercontent.com/in/68672?v=4&s=60)
[pre-commit.ci] auto fixes from pre-commit.com hooks
fbba8a6a
fixtypo
4d097f8b
fixtypo
024dfc0b
[pre-commit.ci] auto fixes from pre-commit.com hooks
925f038f
fix ut typo
d7681f91
[pre-commit.ci] auto fixes from pre-commit.com hooks
7c2c255b
wenhuach21
commented
on 2025-11-21
wenhuach21
commented
on 2025-11-24
wenhuach21
commented
on 2025-11-24
xin3he
approved these changes
on 2025-11-25
Merge branch 'support_mxfp_nvfp_lmhead_quant' of https://github.com/i…
5c921613
refine logs, fix pack_layer for awq&gptq
a35f8040
Merge branch 'main' of https://github.com/intel/auto-round into suppo…
3b3b666e
refine log, fix pack_layer for awq&gptq
cc780961
Merge branch 'support_mxfp_nvfp_lmhead_quant' of https://github.com/i…
d461adf8
[pre-commit.ci] auto fixes from pre-commit.com hooks
a6b914bd
fixtypo
4d807c04
wenhuach21
commented
on 2025-11-27
add awq&gptq lm_head UT
17c71f76
[pre-commit.ci] auto fixes from pre-commit.com hooks
f96274d2
fix local path
31a30c7d
Merge branch 'support_mxfp_nvfp_lmhead_quant' of https://github.com/i…
6f8f4a50
Login to write a write a comment.
Login via GitHub