Julien Denize 1a20d23dab [PARSER][Mistral] unified engine-based parser for reasoning and tool calls (#48947)

2026-07-30 15:38:00 +02:00

..

chat_completion

[PARSER][Mistral] unified engine-based parser for reasoning and tool calls (#48947)

2026-07-30 15:38:00 +02:00

completion

[Frontend] expose stream_interval as req sampling param (#49754)

2026-07-27 11:30:37 +08:00

engine

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

models

[Frontend] Refactor ServingTokenization entrypoint. (#46022)

2026-06-22 06:27:58 +00:00

parser

[Bugfix] GPT-OSS Autodrop reasoning in Response API and cleanup (#45048)

2026-06-23 09:36:33 -04:00

responses

[Model] Add Kimi K3 support: Python frontend [2/2] (#50093)

2026-07-29 01:06:01 -07:00

__init__.py

Change the name to vLLM (#150)

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

api_server.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

cli_args.py

[Frontend] add per-request timing metrics field to response body of Chat/Completions APIs (#46768)

2026-07-06 17:48:29 -07:00

dp_supervisor.py

[Rust][Benchmark] Make vllm bench serve Rust delegation opt-in (#50081)

2026-07-28 16:21:12 +00:00

run_batch.py

[fix][run_batch]: respect proxy env vars when downloading media URLs (#47697)

2026-07-06 12:45:48 +00:00