JooHo LeeandJooHo Lee a07765c6bd [Bugfix] Fix Qwen3-ASR transcription streaming postprocessing (#42478) ...

Signed-off-by: JooHo Lee <BWAAEEEK@users.noreply.github.com>
Signed-off-by: JooHo Lee <jooho414@gmail.com>
Co-authored-by: JooHo Lee <BWAAEEEK@users.noreply.github.com>

2026-07-09 00:33:27 -07:00

..

anthropic

[Bugfix][Frontend] Emit a content block for empty Anthropic completions (#46525)

2026-06-24 00:04:26 +00:00

cli

[Frontend] Limit SO_REUSEPORT to multi-worker serving (#47529)

2026-07-04 01:26:24 +00:00

generate

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

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

mcp

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

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

openai

[Frontend] Support bad_words in the /v1/completions endpoint (#46793)

2026-07-08 09:51:17 +00:00

pooling

[Bugfix][Pooling] Align CrossEncoder token type ids after truncation (#47772)

2026-07-08 03:59:22 +00:00

scale_out

fix: use configured max_logprobs instead of hardcoded 20 in derender validation (#47834)

2026-07-07 09:42:47 +00:00

serve

[CI] GSM8K eval integration test for KV offloading (#46893)

2026-07-08 17:59:48 -04:00

speech_to_text

[Bugfix] Fix Qwen3-ASR transcription streaming postprocessing (#42478)

2026-07-09 00:33:27 -07:00

__init__.py

Change the name to vLLM (#150)

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

chat_utils.py

[CI] Stabilize the multi-audio OpenAI server path (#44051)

2026-06-07 15:54:32 +08:00

grpc_server.py

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

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

launcher.py

[Logs Refactor] Optimize shutdown logs, easier to follow and consistent (#43707)

2026-06-04 14:36:32 -04:00

llm.py

Weight sync refactor + move sparse nccl engine (#44353)

2026-07-01 01:25:19 -07:00

offline_utils.py

[Frontend] Split the offline inference APIs and utils. (#43553)

2026-05-26 05:20:24 +00:00