tomeras91 5a60699c45 [Bugfix]: Fix the logic for deciding if tool parsing is used (#8366)

2024-09-12 03:55:30 +00:00

..

rpc

[Benchmark] Add --async-engine option to benchmark_throughput.py (#7964)

2024-09-03 20:57:41 -04:00

tool_parsers

[Bugfix] Streamed tool calls now more strictly follow OpenAI's format; ensures Vercel AI SDK compatibility (#8272)

2024-09-09 10:45:11 -04:00

__init__.py

Change the name to vLLM (#150)

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

api_server.py

[Core] Support load and unload LoRA in api server (#6566)

2024-09-05 18:10:33 -07:00

cli_args.py

[Feature] OpenAI-Compatible Tools API + Streaming for Hermes & Mistral models (#5649)

2024-09-04 13:18:13 -07:00

logits_processors.py

[mypy] Enable following imports for entrypoints (#7248)

2024-08-20 23:28:21 -07:00

protocol.py

[Bugfix] Streamed tool calls now more strictly follow OpenAI's format; ensures Vercel AI SDK compatibility (#8272)

2024-09-09 10:45:11 -04:00

run_batch.py

[misc] remove engine_use_ray (#8126)

2024-09-11 18:23:36 -07:00

serving_chat.py

[Bugfix]: Fix the logic for deciding if tool parsing is used (#8366)

2024-09-12 03:55:30 +00:00

serving_completion.py

[mypy] Enable following imports for entrypoints (#7248)

2024-08-20 23:28:21 -07:00

serving_embedding.py

[Bugfix]: Use float32 for base64 embedding (#7855)

2024-08-26 03:16:38 +00:00

serving_engine.py

[Core] Support load and unload LoRA in api server (#6566)

2024-09-05 18:10:33 -07:00

serving_tokenization.py

[Frontend] Clean up type annotations for mistral tokenizer (#8314)

2024-09-10 16:49:11 +00:00