reduce ram&vram usage for vlm calib stage #1488
WeiweiZhang1
merged
13 commits into
main
from
reduce_vram/ram_usage_for_vlm_in_calib_stage
reduce ram usage for vlm calib stage
b1c79a76
Merge branch 'main' into reduce_vram/ram_usage_for_vlm_in_calib_stage
31aa2f59
![pre-commit-ci[bot]](https://avatars.githubusercontent.com/in/68672?v=4&s=60)
[pre-commit.ci] auto fixes from pre-commit.com hooks
0c225237
wenhuach21
commented
on 2026-03-03
gguf better support for transformers5.0 and fix bug of Qwen3Next (#1474)
3a490376
Merge branch 'main' into reduce_vram/ram_usage_for_vlm_in_calib_stage
e3f1fdbd
fix meta issue for patch model
736e7f38
[pre-commit.ci] auto fixes from pre-commit.com hooks
54e1a7c4
fix meta issue of patching model like qwen3.5-35B-A3B
576a417f
fix scan issue
cf668ce6
refine early stop calib logic, add ut for mllm calib cache check
d7c67d7c
[pre-commit.ci] auto fixes from pre-commit.com hooks
fa4f342a
Merge branch 'main' into reduce_vram/ram_usage_for_vlm_in_calib_stage
c7f81d01
yiliu30
approved these changes
on 2026-03-06
Merge branch 'main' into reduce_vram/ram_usage_for_vlm_in_calib_stage
0e8b48e2
wenhuach21
commented
on 2026-03-09
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub