Konrad Zawora 96f6a7596f

[Bugfix] Fix HPU multiprocessing executor (#12167) ...

Signed-off-by: Konrad Zawora <kzawora@habana.ai>

2025-01-23 02:07:07 +08:00

..

multiprocessing

[Bugfix] fix race condition that leads to wrong order of token returned (#10802)

2025-01-21 09:47:04 -08:00

output_processor

[BUGFIX] When skip_tokenize_init and multistep are set, execution crashes (#12277)

2025-01-21 23:30:46 +00:00

__init__.py

Change the name to vLLM (#150)

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

arg_utils.py

[Bugfix] Fix HPU multiprocessing executor (#12167)

2025-01-23 02:07:07 +08:00

async_llm_engine.py

[core] platform agnostic executor via collective_rpc (#11256)

2025-01-15 13:45:21 +08:00

async_timeout.py

[Bugfix] AsyncLLMEngine hangs with asyncio.run (#5654)

2024-06-19 13:57:12 -07:00

llm_engine.py

[Core] Support fully transparent sleep mode (#11743)

2025-01-22 14:39:32 +08:00

metrics_types.py

monitor metrics of tokens per step using cudagraph batchsizes (#11031)

2024-12-09 22:35:36 -08:00

metrics.py

monitor metrics of tokens per step using cudagraph batchsizes (#11031)

2024-12-09 22:35:36 -08:00

protocol.py

[Bugfix] Validate lora adapters to avoid crashing server (#11727)

2025-01-10 15:56:36 +08:00