auto-round
Support tensor parallelism and LoRA, and optimize FP4 MoE performance.
#2567
Open

Support tensor parallelism and LoRA, and optimize FP4 MoE performance. #2567

wenhuach21 wants to merge 39 commits into main from support_tp
wenhuach21
wenhuach21 Add QAD (quantization-aware distillation) with LFQ loss + Top-K teach…
0edc5dc8
wenhuach21 update
d774354d
wenhuach21 Merge remote-tracking branch 'origin/main' into new_qad
2d3e4ef9
wenhuach21 update
76dd84e1
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
2045dbcb
wenhuach21 fix
bd0487ce
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
18ccd2da
wenhuach21 Merge branch 'main' into new_qad
96e2a744
wenhuach21 Merge branch 'main' into new_qad
538a6e5e
wenhuach21 fix
7df652a3
wenhuach21 Merge branch 'new_qad' of https://github.com/intel/auto-round into ne…
1d53ac22
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
173e748c
Copilot Merge remote-tracking branch 'origin/main' into new_qad
d127dcaa
wenhuach21 fix ut
baccd7ae
wenhuach21 Merge branch 'new_qad' of https://github.com/intel/auto-round into ne…
fdb641cc
wenhuach21 refine design
93fc2298
wenhuach21 refine
c934866b
wenhuach21 refine lfq and fix act qad
bbfd7222
wenhuach21 Merge branch 'main' into new_qad
160fe904
wenhuach21 fix review comments
9b65f1b1
wenhuach21 fix review comments
751acfdf
wenhuach21 fix review comments
82ef90cf
wenhuach21 fix ut
cb5ff471
wenhuach21 naive tp in qad
163cf2e1
wenhuach21 update
b5b89637
wenhuach21 update
4e07d4b6
wenhuach21 wenhuach21 requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 1 day ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-11-02
wenhuach21 Merge branch 'main' into support_tp
59c55217
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
cf67e038
AutoRoundBot
wenhuach21 add lora support
b800f491
wenhuach21 Merge branch 'support_tp' of https://github.com/intel/auto-round into…
a983c62c
wenhuach21 speedup nvfp4
16c3aef1
wenhuach21 wenhuach21 changed the title Support tp Support tensor parallelism and LoRA, and optimize NVFP4 MoE performance. 16 hours ago
wenhuach21 update
daa0f42c
wenhuach21 wenhuach21 changed the title Support tensor parallelism and LoRA, and optimize NVFP4 MoE performance. Support tensor parallelism and LoRA, and optimize FP4 MoE performance. 15 hours ago
wenhuach21 Merge main into support_tp and unify DP/TP execution
4160c750
wenhuach21 update
2a2e6678
wenhuach21 update
2e726739
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
94290d8c
AutoRoundBot
wenhuach21 update
a7be54e5
wenhuach21 update
54c994bc
wenhuach21 update
86386633
wenhuach21 wenhuach21 requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 8 hours ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-11-03

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone