Walter Beller-Morales 8be263c3fb [Core] Cleanup shm based object store on engine shutdown (#32429) ...

Signed-off-by: walterbm <walter.beller.morales@gmail.com>

2026-01-20 08:53:37 +00:00

..

__init__.py

[Feature] Support recording expert indices for rollout router replay (#28284)

2026-01-12 06:23:04 -08:00

async_llm.py

[Core] Cleanup shm based object store on engine shutdown (#32429)

2026-01-20 08:53:37 +00:00

coordinator.py

[Bugfix] Strengthen the check of X-data-parallel-rank in Hybrid LB mode (#32314)

2026-01-15 16:31:16 +08:00

core_client.py

[Bugfix] Strengthen the check of X-data-parallel-rank in Hybrid LB mode (#32314)

2026-01-15 16:31:16 +08:00

core.py

[2/N] Move cache factories to MM registry (#32382)

2026-01-15 01:02:30 -08:00

detokenizer.py

[Misc] Update TokenizerLike interface and move get_cached_tokenizer (#29730)

2025-11-30 14:59:47 +08:00

exceptions.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

input_processor.py

[Core] Cleanup shm based object store on engine shutdown (#32429)

2026-01-20 08:53:37 +00:00

llm_engine.py

[code clean] remove duplicate check (#32376)

2026-01-15 05:29:34 +00:00

logprobs.py

[Bugfix] vLLM produces invalid UTF-8 tokens and “�” (#28874)

2026-01-06 00:23:00 +00:00

output_processor.py

[Feature] Support recording expert indices for rollout router replay (#28284)

2026-01-12 06:23:04 -08:00

parallel_sampling.py

[Core] Add a random suffix to frontend-provided request IDs (#27987)

2025-12-23 13:05:39 -08:00

utils.py

[Bugfix] Strengthen the check of X-data-parallel-rank in Hybrid LB mode (#32314)

2026-01-15 16:31:16 +08:00