elilzhu f9535cc9e2 [BugFix] fix qwenVL quant assertion error (#3466) ...

### What this PR does / why we need it?
This PR fixes issues:
1. Solve the problem that multimodal scene cannot do weight prefetching
and throw an assertion error exception.
2. Standardize the grid_thw data type of qwen2VL to torch.int32.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
- ci & e2e

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: elilzhu <2435754260@qq.com>
Co-authored-by: zhulei (AK) <z00692222@china.huawei.com>

2025-10-16 17:08:00 +08:00

..

layers

[Feat] Flash comm allgher ep (#3334)

2025-10-15 19:36:32 +08:00

__init__.py

[MoE] [Refactor] Combine common_fused_moe and fused_moe (#3176)

2025-10-09 14:12:46 +08:00

deepseek_mtp.py

[KVCache][Bugfix] Fix kv cache initialization error of attention layer (#3113)

2025-09-24 11:32:34 +08:00

deepseek_v2.py

[Feat] Flash comm allgher ep (#3334)

2025-10-15 19:36:32 +08:00

deepseek_v3.py

[CI] Update vllm version to 20250922(5aeb925) (#3091)

2025-09-22 22:18:13 +08:00

qwen2_5_vl_without_padding.py

Drop 0.10.2 (#3284)

2025-10-09 10:28:38 +08:00

qwen2_5_vl.py

Drop 0.10.2 (#3284)

2025-10-09 10:28:38 +08:00

qwen2_vl.py

[BugFix] fix qwenVL quant assertion error (#3466)

2025-10-16 17:08:00 +08:00

qwen3_next.py

[BugFix] Fix Qwen3-Next because of vllm #24982 (#3221)

2025-09-29 15:27:30 +08:00