vllm/tests/v1/streaming_input at ci/narrow-basic-correctness-deps - vllm

obscura/vllm

Fork 0

mirror of https://github.com/vllm-project/vllm.git synced 2026-08-24 06:30:19 +00:00

Files

T

History

68dd7db810 [Reasoning] Support for speculative decoding with thinking budget (#34668 )

Signed-off-by: rishitdholakia13 <[email protected]>
Signed-off-by: rishitdholakia13 <[email protected]>
Co-authored-by: Nick Hill <[email protected]>
Co-authored-by: Cyrus Leung <[email protected]>

2026-04-29 06:14:52 +00:00

__init__.py

[Feature] add session based streaming input support to v1 (#28973 )

2026-01-24 12:06:28 -08:00

test_async_llm_streaming.py

[Renderer] Move InputPreprocessor into Renderer (1/2) (#34510 )

2026-02-14 10:14:21 -08:00

test_gpu_model_runner_streaming.py

[Reasoning] Support for speculative decoding with thinking budget (#34668 )

2026-04-29 06:14:52 +00:00

test_gpu_model_runner_v2_streaming.py

[Model Runner V2] Support Streaming Inputs (#37028 )

2026-03-20 20:42:25 +00:00

test_scheduler_streaming.py

[Feat] DeepSeek V4 Rebased (#40860 )

2026-04-26 18:31:08 -07:00