Andreas KaratzasandGitHub d28bdf9344 [ROCm][CI] Fix ROCm LoRA Transformers fallback with full CUDA graphs (#41577) ...

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

2026-05-23 04:31:32 +00:00

..

__init__.py

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

2026-04-02 12:42:29 +00:00

base.py

[ROCm][CI] Fix ROCm LoRA Transformers fallback with full CUDA graphs (#41577)

2026-05-23 04:31:32 +00:00

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

[MoE Refactor] Rename FusedMoE.make_expert_params_mapping to fused_moe_make_expert_params_mapping (#40671)

2026-04-23 11:22:34 -04:00

multimodal.py

[Perf][4/n] Eliminate various GPU<->CPU syncs (#42347)

2026-05-19 10:35:54 -04:00

pooling.py

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

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

utils.py

Add new tp plan styles to the Transformers modelling backend (#40467)

2026-04-21 08:51:30 -07:00