Oliver HolworthyandOpenAI Codex 28b484e5d7 [Model] Pixtral: use packed multimodal encoder attention (#52185) ...

Signed-off-by: Oliver Holworthy <1216955+oliverholworthy@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>

2026-08-26 14:14:40 +00:00

..

generation

[Model] Pixtral: use packed multimodal encoder attention (#52185)

2026-08-26 14:14:40 +00:00

generation_ppl_test

[Model] Fused mm preprocess normalisation on the Device (#50411)

2026-08-06 03:11:14 -07:00

pooling

[Bugfix][Multimodal] Encode text in mixed CLIP/SigLIP pooling batches (#53165)

2026-08-24 10:45:42 -07:00

processing

[Bugfix][Processor] Replace bare asserts with ValueError in DeepseekVLV2/OCR processors (#53854)

2026-08-26 09:10:54 +00:00

__init__.py

[CI/Build] Move model-specific multi-modal processing tests (#11934)

2025-01-11 13:50:05 +08:00

conftest.py

[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907)

2026-08-11 14:19:16 -04:00

test_mapping.py

[bugfix] Fix Cosmos3 Edge checkpoint weights filtering, video loading, prompt expansion (#49190)

2026-07-21 17:18:36 +08:00

test_mimo_v2_omni.py

[Bugfix][MiMo] Apply vision attention sinks in the window attention path (#49815)

2026-08-10 22:36:42 +00:00

test_nano_nemotron_vl.py

fix(security): enforce audio decode duration limit in NanoNemotronVL (#50221)

2026-08-13 03:31:55 -07:00