Andreas Karatzas 9261dbbc55 Treat null completion max_tokens like the default (#45491) ...

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

2026-06-13 09:34:09 +00:00

..

chat_completion

[Render] Add /derender endpoints for disaggregated postprocessing (#43606)

2026-06-13 13:55:33 +08:00

completion

Treat null completion max_tokens like the default (#45491)

2026-06-13 09:34:09 +00:00

engine

[Render] Add /derender endpoints for disaggregated postprocessing (#43606)

2026-06-13 13:55:33 +08:00

models

[Frontend] Consolidate online serving utils. (#44479)

2026-06-04 06:49:31 +00:00

parser

[Refactor] Deprecate ResponsesParser wrapper, inline parsing into ParsableContext (#45431)

2026-06-12 16:15:41 -04:00

responses

[Refactor] Deprecate ResponsesParser wrapper, inline parsing into ParsableContext (#45431)

2026-06-12 16:15:41 -04:00

__init__.py

Change the name to vLLM (#150)

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

api_server.py

[Frontend] Support strict mode for tool calling (#45003)

2026-06-12 07:51:48 +00:00

cli_args.py

[Frontend] Consolidate online serving utils. (#44479)

2026-06-04 06:49:31 +00:00

dp_supervisor.py

[Feature] SSL support for dp supervisor (#43688)

2026-05-29 19:28:12 +00:00

run_batch.py

[Frontend] Consolidate online serving utils. (#44479)

2026-06-04 06:49:31 +00:00