5 people 29468dde8b [Bugfix][KV Cache][MLA] Align packed block strides for V3.2 sparse MLA (#55528) ...

Signed-off-by: lz <145014769+200lz@users.noreply.github.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-09-25 05:33:36 +00:00

..

__init__.py

[Bugfix][Model Loader] Defer post-load attention weight processing (#49519)

2026-08-10 19:16:57 -07:00

attention.py

[Kernel] Resubmit PR 48666 - Gemma4 FP8 KV FA4 head dim 512 backend selection (#53175)

2026-09-23 20:29:06 -07:00

chunked_local_attention.py

[Attention]: Use KVCacheSpec for AttentionMetadataBuilder type hints (#50148)

2026-07-31 11:20:18 +00:00

cross_attention.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

encoder_only_attention.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

kv_transfer_utils.py

[compile] Allow strings in custom ops without regressing compilation times (#38123)

2026-04-10 07:26:37 +00:00

mla_attention.py

[Bugfix][KV Cache][MLA] Align packed block strides for V3.2 sparse MLA (#55528)

2026-09-25 05:33:36 +00:00

mm_encoder_attention.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

prefill_prefix_lm_attention.py

[Model] Add HrmTextForCausalLM (Hierarchical Reasoning Model — Text) (#43098)

2026-06-16 22:41:41 +08:00

rswa_attention.py

[Model] Support Unlimited OCR (#46564)

2026-06-27 23:09:18 -07:00

sparse_mla_attention.py

[Perf][GLM-5.3-Flash] Dense/masked-MHA sparse prefill for the NoPE (256, 0, 256) layout + skip the NoPE K concat (#55738)

2026-09-14 09:36:39 +00:00

sparse_mla_mask.py

[Attention] Vectorize sparse MLA mask loads (#52217)

2026-08-18 20:32:41 -07:00

static_sink_attention.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00