3 people fa6ae31177 feat: rename logit_bias/logit_scale to logit_mean/logit_sigma for affine score calibration (#39530) ...

Signed-off-by: Jesus Federico <jefp@amazon.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>

2026-04-13 04:43:44 +00:00

..

seqwise

feat: rename logit_bias/logit_scale to logit_mean/logit_sigma for affine score calibration (#39530)

2026-04-13 04:43:44 +00:00

tokwise

feat: rename logit_bias/logit_scale to logit_mean/logit_sigma for affine score calibration (#39530)

2026-04-13 04:43:44 +00:00

__init__.py

[Model] Reorganize pooling layers (#31973)

2026-01-09 11:02:14 +00:00

abstract.py

[Model] Reorganize pooling layers (#31973)

2026-01-09 11:02:14 +00:00

activations.py

[Model] Deprecate the score task (this will not affect users). (#37537)

2026-03-20 08:07:56 +00:00

common.py

[Perf] Remove redundant device copies for CPU-only pooling token IDs, 48.9% E2E throughput improvement (#38139)

2026-03-29 18:12:50 +00:00

special.py

[Perf] Remove redundant device copies for CPU-only pooling token IDs, 48.9% E2E throughput improvement (#38139)

2026-03-29 18:12:50 +00:00