vllm/vllm/entrypoints/pooling at 234860399b9d390bf59bfe1f19c2e2304ac5c806 - vllm - Gitea: Git with a cup of tea

biondizzle/vllm

Files

History

Wentao Ye 7279374f91 [Perf] Compute maxsim in worker side, reducing redundant copies, 2.7% E2E throughput improvement (#36159 )

Signed-off-by: yewentao256 <zhyanwentao@126.com>

2026-03-09 20:55:58 -07:00

..

[Frontend][2/n] Improve pooling entrypoints | embed. (#36110 )

2026-03-09 11:42:19 +08:00

[Frontend][2/n] Improve pooling entrypoints | embed. (#36110 )

2026-03-09 11:42:19 +08:00

[Frontend][2/n] Improve pooling entrypoints | embed. (#36110 )

2026-03-09 11:42:19 +08:00

[Frontend][2/n] Improve pooling entrypoints | embed. (#36110 )

2026-03-09 11:42:19 +08:00

[Perf] Compute maxsim in worker side, reducing redundant copies, 2.7% E2E throughput improvement (#36159 )

2026-03-09 20:55:58 -07:00

__init__.py

[Perf] Compute maxsim in worker side, reducing redundant copies, 2.7% E2E throughput improvement (#36159 )

2026-03-09 20:55:58 -07:00

io_processor_factories.py

[Frontend][2/n] Improve pooling entrypoints | embed. (#36110 )

2026-03-09 11:42:19 +08:00

typing.py

[Frontend][2/n] Improve pooling entrypoints | embed. (#36110 )

2026-03-09 11:42:19 +08:00

utils.py

[Frontend][2/n] Improve pooling entrypoints | embed. (#36110 )

2026-03-09 11:42:19 +08:00