afeldman-nm befc402d34

[V1] V1 engine implements parallel sampling (AsyncLLM and LLMEngine) (#10980) ...

Signed-off-by: Andrew Feldman <afeldman@neuralmagic.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

2025-02-24 08:29:41 -08:00

..

core

[V1][Spec decode] Move drafter to model runner (#13363)

2025-02-17 15:40:12 -08:00

e2e

…

engine

[V1] V1 engine implements parallel sampling (AsyncLLM and LLMEngine) (#10980)

2025-02-24 08:29:41 -08:00

entrypoints

[V1] V1 engine implements parallel sampling (AsyncLLM and LLMEngine) (#10980)

2025-02-24 08:29:41 -08:00

sample

[v1] Support allowed_token_ids in v1 Sampler (#13210)

2025-02-22 14:13:05 +08:00

spec_decode

…

worker

[v1] Support allowed_token_ids in v1 Sampler (#13210)

2025-02-22 14:13:05 +08:00

__init__.py

…

test_stats.py

…

test_utils.py

…