RioSandChauncey e2d49ec2a4 [Bugfix] missing tokens occur in harmony streaming (#30437) ...

Signed-off-by: RioS <aa248424@gmail.com>
Signed-off-by: Ri0S <aa248424@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>

2026-01-09 03:59:34 +00:00

..

anthropic

[Frontend] Fixes anthropic streaming message_start usage nesting (#30266)

2025-12-12 16:28:54 +00:00

cli

Add Multimodal Processor Benchmark (#29105)

2026-01-01 19:26:53 -08:00

openai

[Bugfix] missing tokens occur in harmony streaming (#30437)

2026-01-09 03:59:34 +00:00

pooling

[Frontend] add continue_final_message parameter to /embeddings endpoint (#31497)

2025-12-30 07:21:13 +00:00

sagemaker

[Refactor] [1/N] to simplify the vLLM serving architecture (#28040)

2025-12-03 01:26:39 -08:00

serve

UX: add vLLM env info in '/server_info' (#31899)

2026-01-07 17:13:02 +00:00

__init__.py

Change the name to vLLM (#150)

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

api_server.py

[Perf] Add skip_clone to SamplingParams for internal request handling (#31041)

2025-12-24 14:35:57 -08:00

chat_utils.py

[Frontend] Support using chat template as custom score template for reranking models (#30550)

2025-12-23 11:19:16 +00:00

constants.py

[responsesAPI][6] Fix multi turn MCP tokenization (#30230)

2025-12-10 10:13:13 +08:00

context.py

[Bugfix] missing tokens occur in harmony streaming (#30437)

2026-01-09 03:59:34 +00:00

grpc_server.py

[grpc] Support gRPC server entrypoint (#30190)

2026-01-07 23:24:46 -08:00

launcher.py

[Chore] Separate out vllm.utils.network_utils (#27164)

2025-10-19 03:06:32 -07:00

llm.py

[Perf] Add skip_clone to SamplingParams for internal request handling (#31041)

2025-12-24 14:35:57 -08:00

logger.py

[log] enable max_log_len trim only when needed (#31482)

2026-01-05 03:55:43 +00:00

renderer.py

[OpenAI] Extend VLLMValidationError to additional validation parameters (#31870)

2026-01-07 14:45:49 +00:00

responses_utils.py

[responsesAPI][8] input/output messages for ResponsesParser (#30158)

2025-12-16 13:54:59 +08:00

score_utils.py

[Models] Allow converting Qwen3-VL into Reranker model (#31890)

2026-01-08 08:10:15 +00:00

ssl.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

tool_server.py

[Frontend] Add tool filtering support to ToolServer (#29224)

2025-12-01 08:03:57 +00:00

tool.py

[responsesAPI][5] ResponsesParser with tools for full MCP python loop (#29798)

2025-12-05 11:11:50 -05:00

utils.py

[Frontend] Improve error message (#31987)

2026-01-08 20:07:03 +00:00