Jialin Ouyang a1d3866dda

[n-gen] DO NOT repeatedly return finished child requests (#28591) ...

Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>

2025-11-13 03:36:07 +00:00

..

__init__.py

[Feature]: Add corrupted request metric to V1 metrics system. (#27306)

2025-11-05 13:45:29 -08:00

async_llm.py

[Metrics] Refactor LoRA state tracking (#26801)

2025-11-10 16:34:36 +08:00

coordinator.py

…

core_client.py

…

core.py

[Perf] Move gc.freeze logic from EngineCoreProc to EngineCore for better coverage (#27896)

2025-11-10 15:34:18 -08:00

detokenizer.py

…

exceptions.py

…

llm_engine.py

[Misc]Fix typo in llm_engine.py (#28584)

2025-11-12 12:59:43 -08:00

logprobs.py

[Perf] Use np.ndarray instead of list[list[int]] to reduce GC overhead (#28245)

2025-11-11 10:28:47 -08:00

output_processor.py

[Metrics] Refactor LoRA state tracking (#26801)

2025-11-10 16:34:36 +08:00

parallel_sampling.py

[n-gen] DO NOT repeatedly return finished child requests (#28591)

2025-11-13 03:36:07 +00:00

processor.py

…

utils.py

[Misc] Replace CUDA_VISIBLE_DEVICES in DP with torch.cuda.set_device for device selection on cuda-like devices (#27564)

2025-10-30 11:41:44 -04:00