lxyand“新颐” 0c8c3f41cf [Bugfix][V1] Sync mamba_block_size via EngineCoreReadyResponse (#50809) ...

Signed-off-by: “新颐” <lxy537258@antgroup.com>
Co-authored-by: “新颐” <lxy537258@antgroup.com>

2026-08-19 16:44:36 +00:00

..

__init__.py

[Bugfix][V1] Sync mamba_block_size via EngineCoreReadyResponse (#50809)

2026-08-19 16:44:36 +00:00

async_llm.py

[Bugfix][V1][Multimodal] Recover from P0/P1 processor cache drift (#46747) (#46747)

2026-08-12 12:06:57 +08:00

coordinator.py

[Bugfix][DP] Don't assume the engines started when forwarding a wake (#51481)

2026-08-18 13:49:35 -07:00

core_client.py

[Bugfix][V1] Sync mamba_block_size via EngineCoreReadyResponse (#50809)

2026-08-19 16:44:36 +00:00

core.py

[Bugfix][V1] Sync mamba_block_size via EngineCoreReadyResponse (#50809)

2026-08-19 16:44:36 +00:00

detokenizer.py

[Bugfix][Spec Decode] Select earliest-completing stop string in check_stop_strings (#49391)

2026-07-23 18:14:06 +08:00

exceptions.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

input_processor.py

[Bugfix] Reject negative token ids as out-of-vocabulary (#51795)

2026-08-14 01:07:29 +00:00

llm_engine.py

[V1][Metrics] Preserve prefix-cache stats on zero-output steps (#48668)

2026-08-09 01:58:38 +00:00

logprobs.py

[Model Runner V2] Add logprob_token_ids support (#40559)

2026-05-01 10:02:03 -07:00

output_processor.py

[Feature] Mask Replay (#49577)

2026-08-13 08:44:31 +00:00

parallel_sampling.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

tensor_ipc.py

Add tensor IPC transfer mechanism for multimodal data (#32104)

2026-03-21 20:10:20 +00:00

utils.py

[ROCm] Give EngineCore cleanup grace after request abort (#52281)

2026-08-19 11:39:59 -05:00