sgl-project/sglang

[Feature] Support `return_hidden_states` in async engine

Geschlossen

#6.528 geöffnet am 22.05.2025

 (1 Kommentar) (0 Reaktionen) (0 zugewiesene Personen)Python (6.216 Forks)auto 404
good first issue

Repository-Metriken

Stars
 (28.442 Sterne)
PR-Merge-Metriken
 (Durchschn. Merge 1T 13h) (1.000 gemergte PRs in 30 T)

Beschreibung

Checklist

Motivation

Currently, it is possible to get hidden states using the offline interface, i.e. Engine.generate, but Engine.async_generate doesn't support this function.

result = await model.async_generate(
        ["hello", "how are you doing?"],
        sampling_params={"temperature": 0, "max_new_tokens": 1},
        return_hidden_states=True)
TypeError: Engine.async_generate() got an unexpected keyword argument 'return_hidden_states'

This can be useful when developing web services where some additional hidden states postprocess logics is done.

Related resources

No response

Contributor Guide