Chauncey 6da0078523

[Feat] Allow custom naming of vLLM processes (#21445) ...

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>

2025-07-24 03:15:23 -07:00

..

__init__.py

Elastic Expert Parallel Initial Support (#20775)

2025-07-18 17:46:09 -07:00

async_llm.py

[DP] Internal Load Balancing Per Node [one-pod-per-node] (#21238)

2025-07-23 20:57:32 -07:00

coordinator.py

[Feat] Allow custom naming of vLLM processes (#21445)

2025-07-24 03:15:23 -07:00

core_client.py

[DP] Internal Load Balancing Per Node [one-pod-per-node] (#21238)

2025-07-23 20:57:32 -07:00

core.py

[Feat] Allow custom naming of vLLM processes (#21445)

2025-07-24 03:15:23 -07:00

detokenizer.py

Support embedding models in V1 (#16188)

2025-06-18 21:36:33 -07:00

exceptions.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

llm_engine.py

[V0 Deprecation] Remove Prompt Adapters (#20588)

2025-07-23 16:36:48 -07:00

logprobs.py

Support embedding models in V1 (#16188)

2025-06-18 21:36:33 -07:00

mm_input_cache.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

output_processor.py

[Core][Model] PrithviMAE Enablement on vLLM v1 engine (#20577)

2025-07-23 11:00:23 -07:00

parallel_sampling.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

processor.py

[V0 Deprecation] Remove Prompt Adapters (#20588)

2025-07-23 16:36:48 -07:00

utils.py

[BugFix] Set CUDA_VISIBLE_DEVICES before spawning the subprocesses (#21211)

2025-07-23 21:44:04 -07:00