Harry Mellor 7d4aedae7c

Handle error when str passed to /v1/audio/transcriptions (#17909) ...

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2025-05-09 19:23:59 +00:00

..

tool_parsers

[Bugfix] Fix mistral model tests (#17181)

2025-04-25 06:03:34 -07:00

__init__.py

Change the name to vLLM (#150)

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

api_server.py

[Frontend] Chat template fallbacks for multimodal models (#17805)

2025-05-07 23:05:54 -07:00

cli_args.py

Only log non-default CLI args for online serving (#17803)

2025-05-07 22:33:29 -07:00

logits_processors.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

protocol.py

Handle error when str passed to /v1/audio/transcriptions (#17909)

2025-05-09 19:23:59 +00:00

run_batch.py

Improve conversion from dataclass configs to argparse arguments (#17303)

2025-04-28 16:22:12 +00:00

serving_chat.py

[Bugfix] fix KeyError on top logprobs are special tokens (#17637)

2025-05-04 19:22:35 -07:00

serving_completion.py

[BugFix]: properly catch templating error when preprocess input (#13976)

2025-03-14 05:58:34 -07:00

serving_embedding.py

Truncation control for embedding models (#14776)

2025-04-30 09:24:57 +08:00

serving_engine.py

[Frontend] Chat template fallbacks for multimodal models (#17805)

2025-05-07 23:05:54 -07:00

serving_models.py

[Misc] Enable vLLM to Dynamically Load LoRA from a Remote Server (#10546)

2025-04-15 22:31:38 +00:00

serving_pooling.py

Truncation control for embedding models (#14776)

2025-04-30 09:24:57 +08:00

serving_score.py

Truncation control for embedding models (#14776)

2025-04-30 09:24:57 +08:00

serving_tokenization.py

Refactor error handling for multiple exceptions in preprocessing (#15650)

2025-03-28 03:27:20 +00:00

serving_transcription.py

[Frontend][Docs] Transcription API streaming (#13301)

2025-03-06 10:39:35 +00:00