Thomas Ortner b8baa31a28 Hardware-agnostic model definition via HF transformer backend (1/N) (#49458) ...

Signed-off-by: Thomas Ortner <boh@zurich.ibm.com>

2026-08-13 11:21:50 +01:00

..

__init__.py

Support MLA properly in the Transformers modeling backend (#48250)

2026-08-04 13:24:11 +01:00

base.py

Fix Gemma 4 for upcoming Transformers version (#49797)

2026-08-10 07:48:26 +00:00

glu.py

Hardware-agnostic model definition via HF transformer backend (1/N) (#49458)

2026-08-13 11:21:50 +01:00

mla.py

Support MLA properly in the Transformers modeling backend (#48250)

2026-08-04 13:24:11 +01:00

moe.py

Fix MLA padding and grouped topk routing in the Transformers modelling backend (#49982)

2026-07-27 18:32:32 +00:00

packed_qkv.py

Fix Gemma 4 for upcoming Transformers version (#49797)

2026-08-10 07:48:26 +00:00

qkv.py

Fix Gemma 4 for upcoming Transformers version (#49797)

2026-08-10 07:48:26 +00:00

rms_norm.py

Hardware-agnostic model definition via HF transformer backend (1/N) (#49458)

2026-08-13 11:21:50 +01:00