Cyrus Leung 79b6ec6aab [Bugfix] Fix inconsistent handling of cache reset (#33481) ...

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

2026-01-31 20:23:41 -08:00

..

basic

[Frontend] Cleanup api server (#33158)

2026-01-27 15:18:10 +00:00

chat_completion

[Frontend] Use new Renderer for Completions and Tokenize API (#32863)

2026-01-31 04:51:15 -08:00

completion

[Frontend] Use new Renderer for Completions and Tokenize API (#32863)

2026-01-31 04:51:15 -08:00

engine

[Bugfix] Fix inconsistent handling of cache reset (#33481)

2026-01-31 20:23:41 -08:00

generate

[Frontend] Frontend will only attach supported tasks corresponding entrypoints. (#33139)

2026-01-27 12:15:43 +00:00

models

[Frontend] Introduce Renderer for processing chat messages (using ModelConfig) (#30200)

2026-01-22 12:44:22 +00:00

parser

Remove deprecated reasoning_content message field (#33402)

2026-01-30 11:48:15 +00:00

realtime

[Realtime API] Adds minimal realtime API based on websockets (#33187)

2026-01-30 18:41:29 +08:00

responses

support return prompt token ids in responses (#33378)

2026-01-31 06:04:20 -08:00

translations

[Bugfix] Fix Qwen3ASR language asr tag in output (#33410)

2026-01-31 05:24:49 +00:00

__init__.py

Change the name to vLLM (#150)

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

api_server.py

[Realtime API] Adds minimal realtime API based on websockets (#33187)

2026-01-30 18:41:29 +08:00

cli_args.py

[Logging] add --disable-access-log-for-endpoints CLI option (#30011)

2026-01-26 21:49:03 +00:00

orca_metrics.py

Add ORCA endpoint load metrics support (#24905)

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

run_batch.py

[Frontend] Score entrypoint support data_1 & data_2 and queries & documents as inputs (#32577)

2026-01-19 14:07:46 +00:00

server_utils.py

[Frontend] Cleanup api server (#33158)

2026-01-27 15:18:10 +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