auto-round
Support tensor parallelism and LoRA, and optimize FP4 MoE performance.
#2567
Open
Open
Support tensor parallelism and LoRA, and optimize FP4 MoE performance. #2567
wenhuach21
wants to merge
39 commits into
main
from
support_tp
Add QAD (quantization-aware distillation) with LFQ loss + Top-K teach…
0edc5dc8
update
d774354d
Merge remote-tracking branch 'origin/main' into new_qad
2d3e4ef9
update
76dd84e1
![pre-commit-ci[bot]](https://avatars.githubusercontent.com/in/68672?v=4&s=60)
[pre-commit.ci] auto fixes from pre-commit.com hooks
2045dbcb
fix
bd0487ce
[pre-commit.ci] auto fixes from pre-commit.com hooks
18ccd2da
Merge branch 'main' into new_qad
96e2a744
Merge branch 'main' into new_qad
538a6e5e
fix
7df652a3
Merge branch 'new_qad' of https://github.com/intel/auto-round into ne…
1d53ac22
[pre-commit.ci] auto fixes from pre-commit.com hooks
173e748c
Merge remote-tracking branch 'origin/main' into new_qad
d127dcaa
fix ut
baccd7ae
Merge branch 'new_qad' of https://github.com/intel/auto-round into ne…
fdb641cc
refine design
93fc2298
refine
c934866b
refine lfq and fix act qad
bbfd7222
Merge branch 'main' into new_qad
160fe904
fix review comments
9b65f1b1
fix review comments
751acfdf
fix review comments
82ef90cf
fix ut
cb5ff471
naive tp in qad
163cf2e1
update
b5b89637
update
4e07d4b6
Merge branch 'main' into support_tp
59c55217
[pre-commit.ci] auto fixes from pre-commit.com hooks
cf67e038
add lora support
b800f491
Merge branch 'support_tp' of https://github.com/intel/auto-round into…
a983c62c
speedup nvfp4
16c3aef1
wenhuach21
changed the title
update
daa0f42c
wenhuach21
changed the title
Merge main into support_tp and unify DP/TP execution
4160c750
update
2a2e6678
update
2e726739
[pre-commit.ci] auto fixes from pre-commit.com hooks
94290d8c
update
a7be54e5
update
54c994bc
update
86386633
copilot-pull-request-reviewer
commented
on 2026-11-03
Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub