kourosh hakhamaneshi 7a8f0a3548 [BugFix] Fix OOM in vLLM replicas by ensuring consistent NCCL memory accounting (#25359) ...

Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>

2025-10-03 13:35:54 -07:00

..

lm-eval-harness

[Deprecation] Remove prompt_token_ids arg fallback in LLM.generate and LLM.embed (#18800)

2025-08-22 10:56:57 +08:00

nightly-benchmarks

[Doc]: fix typos in various files (#24821)

2025-09-15 01:08:52 -07:00

scripts

[TPU][Bugfix][CI] Fix broken tests/build dependency (#25255)

2025-10-03 13:35:53 -07:00

check-wheel-size.py

[Attention] FlashAttn MLA (#14258)

2025-09-04 02:47:59 -07:00

generate_index.py

[ci/build] Fix abi tag for aarch64 (#23329)

2025-08-21 23:32:55 +08:00

pyproject.toml

[Doc] Move examples and further reorganize user guide (#18666)

2025-05-26 07:38:04 -07:00

release-pipeline.yaml

[ci] fix wheel names for arm wheels (#24898)

2025-09-15 14:39:08 -07:00

test-pipeline.yaml

[BugFix] Fix OOM in vLLM replicas by ensuring consistent NCCL memory accounting (#25359)

2025-10-03 13:35:54 -07:00