Roger Wang 8bf6266a17

[Multimodal] Generate mm_hash based on request metadata when caching is turned off (#23690) ...

Signed-off-by: Roger Wang <hey@rogerw.io>

2025-08-27 20:24:31 +00:00

..

__init__.py

[Refactor] Allow optional MultiModalKwargsItem in IPC (#23022)

2025-08-16 11:30:49 +00:00

async_llm.py

[Core] Use key-only cache for BaseMultiModalProcessor (#23018)

2025-08-27 14:19:13 +08:00

coordinator.py

[BugFix] Improve internal DP load balancing (#21617)

2025-08-01 19:45:27 -07:00

core_client.py

[Misc] Remove unnecessary _send_reconfig_message() in core_client.py (#23127)

2025-08-27 05:50:47 -07:00

core.py

[XPU] Fix OOM issue for data parallel with Ray backend (#22500)

2025-08-27 19:57:38 +08:00

detokenizer.py

[V1] support min_tokens for detokener (#22014)

2025-08-16 02:28:10 +00:00

exceptions.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

llm_engine.py

[Core] Use key-only cache for BaseMultiModalProcessor (#23018)

2025-08-27 14:19:13 +08:00

logprobs.py

[Sampler] Support returning all logprobs or logits (#21792)

2025-08-04 03:04:12 -07:00

output_processor.py

[Core] Return final response for aborted requests from AsyncLLM.generate (#22283)

2025-08-14 14:49:02 -07:00

parallel_sampling.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

processor.py

[Multimodal] Generate mm_hash based on request metadata when caching is turned off (#23690)

2025-08-27 20:24:31 +00:00

utils.py

[XPU] Fix OOM issue for data parallel with Ray backend (#22500)

2025-08-27 19:57:38 +08:00