vllm-project/vllm

[Feature]: Support `Phi4Flash` model in V1

Open

#23.957 aperta il 29 ago 2025

Vedi su GitHub
 (7 commenti) (0 reazioni) (0 assegnatari)Python (16.816 fork)batch import
feature requestgood first issuehelp wantedstaleunstale

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

We will drop support for V0 in the very near future, and if we want to continue supporting this model in vLLM, it needs to be ported to V1.

The main work here is in:

  1. Adapting the custom Mamba layer to match how V1 manages the mamba state. The MambaMixer, MambaMixer2, MinimaxLinearAttention and ShortConv can all be used as a reference for how to do this.
  2. Porting the differential attention backend to V1.

Alternatives

Drop model support in vLLM

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