vllm-project/vllm

[Feature]: Remove attention layer name from `unified_kv_cache_update`

Open

#33.267 aberto em 28 de jan. de 2026

Ver no GitHub
 (8 comments) (1 reaction) (2 assignees)Python (16.816 forks)batch import
feature requestgood first issuehelp wantedstalestartup-uxtorch.compile

Métricas do repositório

Stars
 (80.034 stars)
Métricas de merge de PR
 (Mesclagem média 9d 2h) (921 fundiu PRs em 30d)

Description

🚀 The feature, motivation and pitch

unified_kv_cache_update appears in piecewise cudagraph regions, and each layer has a different name, so each of these have to be compiled separately. This increases cold start compilation time with Dynamo partition because the graphs can no longer be reused.

We should use the same approach as #32805 and #33184 to iterate through the layers in the forward context.

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Guia do colaborador