3 people 4731884796 [Feature] limit thinking tokens (hard limit) (#20859) ...

Signed-off-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com>
Signed-off-by: Sungjae Lee <sung-jae.lee@navercorp.com>
Signed-off-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2026-03-24 09:53:07 -07:00

..

chat_completion

[Feature] limit thinking tokens (hard limit) (#20859)

2026-03-24 09:53:07 -07:00

completion

[CI][Bugfix] Fix 500 errors from priority overflow and TemplateError subclasses in schema fuzz tests (#37127)

2026-03-16 05:27:21 +00:00

engine

Fix tool_parser_cls type annotation from Callable to type[ToolParser] (#37957)

2026-03-23 22:58:27 -07:00

generate

[Frontend][Bugfix] Pass default_chat_template_kwargs to AnthropicServingMessages (#37899)

2026-03-24 05:00:12 +00:00

models

[Frontend] Split OpenAIServingModels into OpenAIModelRegistry + OpenAIServingModels (#36536)

2026-03-12 03:29:37 -07:00

parser

Fix tool_parser_cls type annotation from Callable to type[ToolParser] (#37957)

2026-03-23 22:58:27 -07:00

realtime

[Chore] Replace all base64 usages with faster pybase64 package (#37290)

2026-03-17 14:44:19 +00:00

responses

Fix tool_parser_cls type annotation from Callable to type[ToolParser] (#37957)

2026-03-23 22:58:27 -07:00

speech_to_text

[Frontend] Remove librosa from audio dependency (#37058)

2026-03-21 11:36:15 +08:00

__init__.py

Change the name to vLLM (#150)

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

api_server.py

[Model] Deprecate the score task (this will not affect users). (#37537)

2026-03-20 08:07:56 +00:00

cli_args.py

[V0 Deprecation] Deprecate --disable-frontend-multiprocessing (#37612)

2026-03-20 11:31:43 +08:00

orca_metrics.py

Add ORCA endpoint load metrics support (#24905)

2025-11-03 08:21:31 +00:00

run_batch.py

[V0 Deprecation] Deprecate --disable-frontend-multiprocessing (#37612)

2026-03-20 11:31:43 +08:00

server_utils.py

[openapi] remove redundant exception stack trace[4/N] (#37157)

2026-03-17 15:06:25 +00:00

utils.py

[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

2026-01-13 13:01:39 +00:00