vllm-project/vllm

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

Open

#33.267 geöffnet am 28. Jan. 2026

Auf GitHub ansehen
 (8 Kommentare) (1 Reaktion) (2 zugewiesene Personen)Python (16.816 Forks)batch import
feature requestgood first issuehelp wantedstalestartup-uxtorch.compile

Repository-Metriken

Stars
 (80.034 Stars)
PR-Merge-Metriken
 (Durchschn. Merge 9T 2h) (921 gemergte PRs in 30 T)

Beschreibung

🚀 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.

Contributor Guide