vllm/tests/entrypoints/pooling at main - vllm - Gitea: Git with a cup of tea

obscura/vllm

mirror of https://github.com/vllm-project/vllm.git synced 2026-08-03 20:38:06 +00:00

Files

T

History

Andreas KaratzasandGitHub 5b95890742 [FlexAttention] Avoid encoder block-mask compile explosion (#50339 )

Signed-off-by: Andreas Karatzas <[email protected]>

2026-07-30 11:24:13 -04:00

..

[Frontend] Overlap preprocessing and computation for pooling models offline inference (#47699 )

2026-07-16 14:00:20 +00:00

[Multimodal] Add Qwen2-VL/Qwen2.5-VL processor-mapped video loader (#45555 )

2026-06-21 18:56:50 +00:00

[FlexAttention] Avoid encoder block-mask compile explosion (#50339 )

2026-07-30 11:24:13 -04:00

Deprecations for v0.23 and v0.24 (#44992 )

2026-06-11 14:35:38 +00:00

[Bugfix] Restore truncate_prompt_tokens for Jina rerank/score online (#49963 )

2026-07-27 22:52:59 +08:00

[Frontend] Remove frontend pooling multi task support. (#37861 )

2026-04-21 12:27:44 +00:00

[Frontend] Remove frontend pooling multi task support. (#37861 )

2026-04-21 12:27:44 +00:00

__init__.py

[CI] Split pooling from entrypoints Test (#24632 )

2025-09-11 01:53:09 -07:00

test_utils.py

[Perf] Use numpy zero-copy path for embedding float response serialization (#41681 )

2026-05-07 19:42:21 -07:00