4 people 3b6c96a101 [Bugfix][Pooling] Fix wrong scores for chunked prefill under torch.compile (#48901) ...

Signed-off-by: seewoo <seewoo@ucsc.edu>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>

2026-07-17 05:19:12 +00:00

..

generation

DCP supports hybrid attention (#40996)

2026-07-09 21:34:45 -07:00

generation_ppl_test

[Core] Support fp32 lm_head for generation models via head_dtype (RFC #48305 §3.6) (#48390)

2026-07-13 16:43:34 +08:00

pooling

[Bugfix][Pooling] Fix wrong scores for chunked prefill under torch.compile (#48901)

2026-07-17 05:19:12 +00:00

pooling_mteb_test

[Model] Remove obsolete ERNIE models (#45127)

2026-06-10 20:54:30 +08:00

__init__.py

[CI/Build] Reorganize models tests (#17459)

2025-04-30 23:03:08 -07:00