Wentao YeandGitHub c34ba6b961 [Perf] Optimize compute maxsim using batched version, 3.2% E2E throughput improvement (#36710) ...

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

2026-03-12 08:37:01 +08:00

..

basic

[Frontend] Use new Renderer for Completions and Tokenize API (#32863)

2026-01-31 04:51:15 -08:00

classify

Fix Qwen2.5-VL test for Transformers v5 (#36532)

2026-03-10 12:05:34 +00:00

embed

feat: expose media_io_kwargs at runtime (#34778)

2026-03-07 04:27:04 +00:00

pooling

[Refactor] Clean up pooling serial utils (#33665)

2026-02-03 10:29:18 +00:00

reward

[Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145)

2025-12-04 13:44:15 +00:00

score

[Perf] Optimize compute maxsim using batched version, 3.2% E2E throughput improvement (#36710)

2026-03-12 08:37:01 +08:00

__init__.py

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

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