auto-round
Add static FP8 attention support
#1061
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
35
Changes
View On
GitHub
Add static FP8 attention support
#1061
yiliu30
merged 35 commits into
main
from
quant-attn
add attention quant
46749f0c
add ut
f743ffba
add llama patch
a81b5145
correct fp8
157f6d13
add utils
586462f8
merge main
591549b2
fix shape
65a467ee
tmp
da1fe7fc
clean code
4f3b0a32
Merge branch 'main' into quant-attn
ae3a4aa7
add ut
ceca38a6
clean
a49c09b7
Merge branch 'quant-attn' of https://github.com/intel/auto-round into…
90bf465f
fix
adc5cb3b
refine
a61bd657
clean
c4bfce03
fix
478eef09
fix
5ed5f724
fix
53f6ae8a
fix
741f818f
fix alias tensor
ae6cec51
fix ut
ffa5ac56
Merge branch 'main' into quant-attn
c7d72d57
Merge branch 'main' into quant-attn
641089df
Merge branch 'main' into quant-attn
61ca489d
update
b698ec43
fix
3b363531
fix
4e541798
Merge branch 'main' into quant-attn
2aaea060
yiliu30
enabled auto-merge (squash)
106 days ago
yiliu30
requested a review
from
n1ck-guo
106 days ago
yiliu30
requested a review
from
wenhuach21
106 days ago
wenhuach21
requested a review
from
xin3he
106 days ago
wenhuach21
commented on 2025-11-25
wenhuach21
commented on 2025-11-25
wenhuach21
commented on 2025-11-25
wenhuach21
commented on 2025-11-25
wenhuach21
commented on 2025-11-25
wenhuach21
commented on 2025-11-25
upadte
cd7a7070
Merge branch 'main' into quant-attn
2743582a
disabled auto-merge
105 days ago
Manually disabled by user
Merge branch 'quant-attn' of https://github.com/intel/auto-round into…
6d1e0abf
update
cc8d06a2
update
a47a0491
wenhuach21
requested a review
from
wenhuach21
105 days ago
wenhuach21
approved these changes on 2025-11-25
Merge branch 'main' into quant-attn
54d6f5ab
yiliu30
merged
6bde0e11
into main
105 days ago
yiliu30
deleted the quant-attn branch
105 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
wenhuach21
n1ck-guo
xin3he
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub