vllm-project/vllm

[Feature]: Extract KV-Cache update from all attention backends

Open

#32.335 aperta il 14 gen 2026

Vedi su GitHub
 (51 commenti) (0 reazioni) (9 assegnatari)Python (16.816 fork)batch import
feature requestgood first issuehelp wanted

Metriche repository

Star
 (80.034 star)
Metriche merge PR
 (Merge medio 3g 17h) (993 PR mergiate in 30 g)

Descrizione

🚀 The feature, motivation and pitch

Similar to how https://github.com/vllm-project/vllm/pull/25954 extracts it from FlashAttn. Ideally, we want to cover all backends with kv-cache update from v1/attention/backends.

Backends:

  • FlashAttention
  • FlashInfer
  • AiterFlashAttention (in progress)
  • RocmAiterUnifiedAttention
  • RocmAttention
  • TritonAttention
  • FlashAttentionDiffKV
  • FlexAttention
  • TreeAttention

MLA Backends:

  • FlashAttnMLA
  • FlashInferMLA
  • FlashMLASparse
  • FlashMLA
  • AiterMLA
  • ROCMAiterMLASparse
  • CutlassMLA
  • TritonMLA

After all backends are supported, we can remove slot_mapping from attention metadata.

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.

Guida contributor