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

[CORE] Support Prefix Caching with Prompt Embeds (#27219)

Browse Source 
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
This commit is contained in:
Andrew Sansom
2025-10-23 00:18:07 -05:00
committed by GitHub
parent 243ed7d32e
commit ff93cc8c84
6 changed files with 185 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/features/README.md
View File

@@ -52,7 +52,7 @@ th:not(:first-child) {
| [mm](multimodal_inputs.md) | ✅ | ✅ | [🟠](https://github.com/vllm-project/vllm/pull/4194)<sup>^</sup> | ❔ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | | | |
| best-of | ✅ | ✅ | ✅ | [❌](https://github.com/vllm-project/vllm/issues/6137) | ✅ | ❌ | ✅ | ✅ | ✅ | ❔ | [❌](https://github.com/vllm-project/vllm/issues/7968) | ✅ | ✅ | | |
| beam-search | ✅ | ✅ | ✅ | [❌](https://github.com/vllm-project/vllm/issues/6137) | ✅ | ❌ | ✅ | ✅ | ✅ | ❔ | [❌](https://github.com/vllm-project/vllm/issues/7968) | ❔ | ✅ | ✅ | |
| [prompt-embeds](prompt_embeds.md) | ✅ | [❌](https://github.com/vllm-project/vllm/issues/25096) | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❔ | ❔ | ❌ | ❔ | ❔ | ✅ |
| [prompt-embeds](prompt_embeds.md) | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❔ | ❔ | ❌ | ❔ | ❔ | ✅ |
\* Chunked prefill and prefix caching are only applicable to last-token pooling.
<sup>^</sup> LoRA is only applicable to the language backbone of multimodal models.
@@ -75,4 +75,4 @@ th:not(:first-child) {
| multi-step | ✅ | ✅ | ✅ | ✅ | ✅ | [❌](https://github.com/vllm-project/vllm/issues/8477) | ✅ | ❌ | ✅ |
| best-of | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ |
| beam-search | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ |
| [prompt-embeds](prompt_embeds.md) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ? | [❌](https://github.com/vllm-project/vllm/issues/25097) | ✅ |
| [prompt-embeds](prompt_embeds.md) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | [❌](https://github.com/vllm-project/vllm/issues/25097) | ✅ |