Luciano MartinsandLuciano Martins 979f5511d7 [Bugfix][Gemma4] Keep image bidirectional attention within the sliding window (#47217) ...

Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>

2026-07-02 19:57:41 -07:00

..

kernels

[Attention][DSA] support dcp for FLASHINFER_MLA_SPARSE (#46076)

2026-07-01 00:32:20 -04:00

layers

[Bugfix][Gemma4] Keep image bidirectional attention within the sliding window (#47217)

2026-07-02 19:57:41 -07:00

model_loader

Remove more unnecessary load_weights methods (#47058)

2026-06-30 15:22:16 +01:00

models

[Bugfix][Gemma4] Keep image bidirectional attention within the sliding window (#47217)

2026-07-02 19:57:41 -07:00

offloader

[Platform] Replace torch.cuda.Event with torch.Event (#47140)

2026-06-30 08:39:59 -07:00

warmup

[Model Runner V2][Perf] Warm up GLM-5.2 DSA indexer prefill metadata kernel (#47285)

2026-07-02 16:31:31 +00:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

Add ability to replace oot ops when using lora (#37181)

2026-03-16 18:04:15 -07:00

parameter.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

utils.py

Remove more unnecessary load_weights methods (#47058)

2026-06-30 15:22:16 +01:00