6 people 153a17166e [Frontend] Add the Beam reasoning and tool parsers (#62052) ...

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Yoni Gozlan <74535834+yonigozlan@users.noreply.github.com>
Co-authored-by: neilkg <33635204+neilkg@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-16 14:08:29 -07:00

..

anthropic

[Frontend] Replace return_mm_kwargs with an mm_payload enum on render requests (#61427)

2026-10-15 12:41:46 +00:00

cli

[Benchmark] Add vllm bench forward: exact-shape forward timing (#61339)

2026-10-14 10:52:26 -07:00

cohere

[Bugfix][Frontend] Reject Cohere REQUIRED tool choice without tools (#61825)

2026-10-15 16:37:08 +00:00

common

[Bugfix] Respect the configured offline chat template (#61061)

2026-10-11 16:27:21 +00:00

generate

[Frontend] Apply each endpoint's top_logprobs cut in derender (#59518)

2026-10-15 15:04:04 +00:00

launchers

[Feature] Add External LB Mode Support for Elastic EP Scaling (#43202)

2026-10-15 21:29:02 -04:00

mcp

[Bugfix][Responses API] Preserve built-in tool output call IDs (#55596)

2026-09-29 22:45:14 +00:00

openai

[Frontend] Add the Beam reasoning and tool parsers (#62052)

2026-10-16 14:08:29 -07:00

pooling

[Bugfix][Frontend] Honor the constructor chat template in offline scoring (#61990)

2026-10-16 10:20:46 +00:00

rl

[RL] Release weight-transfer communicators without stopping inference (#61060)

2026-10-11 21:15:14 +08:00

scale_out

[Frontend] Apply each endpoint's top_logprobs cut in derender (#59518)

2026-10-15 15:04:04 +00:00

serve

[Feature] Add External LB Mode Support for Elastic EP Scaling (#43202)

2026-10-15 21:29:02 -04:00

speech_to_text

[Bugfix][Model] Voxtral realtime: fix boot OOM and engine crash at max_model_len (#45022)

2026-10-09 17:40:29 +08:00

__init__.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

grpc_server.py

[Frontend] Move grpc_server to launchers. (#56746)

2026-09-14 05:03:08 +00:00

llm.py

[Bugfix][Frontend] Support scalar priority and wire priority into LLM.chat() (#57243)

2026-10-11 10:03:33 +00:00