PR #1182 Enable qwen3 vl moe quant and load

Enable qwen3 vl moe quant and load #1182

yiliu30 merged 9 commits into main from enable_qwen3_vl_moe_quant

refine update_fused_layer_global_scales to fix device mismatch for nv…

09b3a1ce

WeiweiZhang1 requested a review from

copilot-pull-request-reviewer 6 days ago

WeiweiZhang1 requested a review from

yiliu30 6 days ago

enable qwen3_vl_moe quantization & quantized model loading

91280321

[pre-commit.ci] auto fixes from pre-commit.com hooks

5d816459

copilot-pull-request-reviewer commented on 2025-12-23

fixtypo

9f61c9e4

Merge branch 'enable_qwen3_vl_moe_quant' of https://github.com/intel/…

8769f04d

WeiweiZhang1 requested a review from

n1ck-guo 6 days ago

yiliu30 approved these changes on 2025-12-23

Merge branch 'main' into enable_qwen3_vl_moe_quant

a39c5513

Update auto_round/modelling/qwen3_vl_moe.py

2afa2698

set calib_all_experts to false

c268e3dc

fix typo

b9b8914a

n1ck-guo commented on 2025-12-24

yiliu30 merged d1935065 into main 4 days ago

yiliu30 deleted the enable_qwen3_vl_moe_quant branch 4 days ago

Reviewers

yiliu30

n1ck-guo

Assignees

No one assigned

Labels

None yet

Milestone

No milestone