vllm/tests/models/transformers at main - vllm - Gitea: Git with a cup of tea

obscura/vllm

Fork 0

mirror of https://github.com/vllm-project/vllm.git synced 2026-08-05 05:18:09 +00:00

Files

T

History

166f4e2dc3 fix: fuse weightless RMSNorms at their declared width (#50867 )

Signed-off-by: Anuj Bolewar <[email protected]>
Signed-off-by: Harry Mellor <[email protected]>
Co-authored-by: Anuj Bolewar <[email protected]>
Co-authored-by: Harry Mellor <[email protected]>

2026-08-04 16:03:09 +00:00

fusers

fix: fuse weightless RMSNorms at their declared width (#50867 )

2026-08-04 16:03:09 +00:00

__init__.py

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

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

test_backend.py

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

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