Skip to content

Conversation

@shen-shanshan
Copy link
Collaborator

What this PR does / why we need it?

Fix: #829

Does this PR introduce any user-facing change?

How was this patch tested?

Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: shen-shanshan <467638484@qq.com>
@wangxiyuan wangxiyuan changed the title [Bugfix] Patch transformer utils [Bugfix][0.7.3] Patch transformer utils May 21, 2025
@wangxiyuan wangxiyuan merged commit e9b819f into vllm-project:v0.7.3-dev May 21, 2025
11 checks passed
wangxiyuan pushed a commit that referenced this pull request May 22, 2025
### What this PR does / why we need it?

Update transformer utils patch for `v0.7.3`.

This PR is a supplement to
#858, adding more patch
methods adapted from vllm-project/vllm#17948 to
solve `revision` problems in more scenarios besides
#829.

### Does this PR introduce _any_ user-facing change?

no.

### How was this patch tested?

```bash
vllm serve Qwen/Qwen2.5-VL-7B-Instruct \
--dtype bfloat16 \
--max_model_len 32768 \
--max-num-batched-tokens 32768
```

Signed-off-by: shen-shanshan <467638484@qq.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants