biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145)

Browse Source 
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2025-12-04 21:44:15 +08:00
committed by GitHub
parent 1b7c7f5159
commit 74c4d80c6c
15 changed files with 224 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/features/README.md
View File

@@ -54,7 +54,7 @@ th:not(:first-child) {
| beam-search | ✅ | ✅ | ✅ | [❌](https://github.com/vllm-project/vllm/issues/6137) | ✅ | ❌ | ✅ | ✅ | ✅ | ❔ | [❌](https://github.com/vllm-project/vllm/issues/7968) | ❔ | ✅ | ✅ | |
| [prompt-embeds](prompt_embeds.md) | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❔ | ❔ | ❌ | ❔ | ❔ | ✅ |
\* Chunked prefill and prefix caching are only applicable to last-token pooling.
\* Chunked prefill and prefix caching are only applicable to last-token or all pooling with causal attention.
<sup>^</sup> LoRA is only applicable to the language backbone of multimodal models.
### Feature x Hardware