auto-round
Refine AutoScheme logic for gguf, reduce memory consumption and improve speed
#1916
Merged
Merged
Refine AutoScheme logic for gguf, reduce memory consumption and improve speed #1916
wenhuach21
merged
47 commits into
main
from
refine_dl
adjust embedding logic
ae07ef0e
update
68ea043c
save some memory
2e7ee5ab
Merge branch 'main' into refine_dl
5e7923b9
rm clear memory to speedup
5c48cd58
rm clear memory to speedup
2194e9f3
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
8e329ef4
![pre-commit-ci[bot]](https://avatars.githubusercontent.com/in/68672?v=4&s=60)
[pre-commit.ci] auto fixes from pre-commit.com hooks
4b7d46dc
wenhuach21
changed the title
wenhuach21
changed the title
adjust
86d7abc1
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
dac0fc8e
[pre-commit.ci] auto fixes from pre-commit.com hooks
431ed624
fix
09df7a0a
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
e4582355
[pre-commit.ci] auto fixes from pre-commit.com hooks
0518ae55
update
dce1e84f
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
714a1db5
[pre-commit.ci] auto fixes from pre-commit.com hooks
2a481171
wenhuach21
changed the title
trigger imatrix, the ram usage is high
23db0ad9
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
09f0edd4
[pre-commit.ci] auto fixes from pre-commit.com hooks
2b1586cd
Merge branch 'main' into refine_dl
d8dab683
save vram at the cost of more ram
5dc89b1d
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
6d3d48f0
[pre-commit.ci] auto fixes from pre-commit.com hooks
d45e0f9f
try to fix vlm issue
94fc769c
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
fbab5627
[pre-commit.ci] auto fixes from pre-commit.com hooks
b6f31402
update
ce7adc3d
update
0f36f673
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
60b8d0d5
[pre-commit.ci] auto fixes from pre-commit.com hooks
616aeebc
fix
4332e3e3
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
d187d86e
[pre-commit.ci] auto fixes from pre-commit.com hooks
9c9c0d6f
Merge branch 'main' into refine_dl
4c441679
only make change to gguf format
d6a33d55
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
482966f0
[pre-commit.ci] auto fixes from pre-commit.com hooks
dcedd555
revert some code
f1fcbe39
Merge branch 'refine_dl' of https://github.com/intel/auto-round into …
aee3b4ab
update
d74a7a13
Potential fix for pull request finding
1f5dd0c0
clean
35ebbe89
Potential fix for pull request finding
e45b2e25
Potential fix for pull request finding
2811d3f9
Potential fix for pull request finding
1970b992
Potential fix for pull request finding
fa362ad5
n1ck-guo
approved these changes
on 2026-06-22
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub