Harry MellorandGitHub 56da398dac Fix embed scaling + CUDA graphs in Transformers modelling backend (#48010) ...

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

2026-07-09 00:14:33 +01:00

..

fusers

[CI] Fix Transformers modeling backend LoRA test (#47832)

2026-07-07 11:40:00 +00:00

__init__.py

Make the Transformers modeling backend as fast as native vLLM (#47187)

2026-07-06 16:59:14 +01:00

base.py

Fix embed scaling + CUDA graphs in Transformers modelling backend (#48010)

2026-07-09 00:14:33 +01:00

causal.py

[Bugfix] Transformers backend: apply learned lm_head.bias for tied-embedding models (#46835)

2026-06-29 08:59:15 +00:00

fuser.py

Make the Transformers modeling backend as fast as native vLLM (#47187)

2026-07-06 16:59:14 +01:00

fx_utils.py

Make the Transformers modeling backend as fast as native vLLM (#47187)

2026-07-06 16:59:14 +01:00

legacy.py

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

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

moe.py

Make the Transformers modeling backend as fast as native vLLM (#47187)

2026-07-06 16:59:14 +01:00

multimodal.py

[Bugfix] Transformers backend: recompute mm_token_type_ids per request for M-RoPE (#46552)

2026-06-28 15:19:28 +00:00

pooling.py

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

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

utils.py

Make the Transformers modeling backend as fast as native vLLM (#47187)

2026-07-06 16:59:14 +01:00