Harry Mellorandkhluu 9a3a31fd2d Don't compile vision encoder for Transformers backend (#30518) ...

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

Signed-off-by: khluu <khluu000@gmail.com>

2026-04-16 17:09:39 -07:00

..

__init__.py

Don't compile vision encoder for Transformers backend (#30518)

2026-04-16 17:09:39 -07:00

base.py

Update to transformers v5 (#30566)

2026-04-16 15:47:49 -07:00

causal.py

Fix pipeline parallel with multimodal models with the Transformers modelling backend (#37057)

2026-03-16 10:20:37 +00:00

legacy.py

[Bugfix] Fix RoBERTa position_ids accumulation on CUDA graph padding (#37884)

2026-03-23 15:15:12 +00:00

moe.py

Enable loading of fused expert weights in the Transformers modelling backend (#36997)

2026-03-14 07:01:06 +00:00

multimodal.py

Don't compile vision encoder for Transformers backend (#30518)

2026-04-16 17:09:39 -07:00

pooling.py

[Doc] Fix duplicate words in comments (#36713)

2026-03-10 21:28:31 -07:00

utils.py

Replace nn.ConvNd with vLLM's ConvNdLayer for Transformers modeling backend (#31498)

2025-12-29 16:20:01 +00:00