v0.25.1: [Bugfix] Guard mixed-dtype allreduce RMSNorm quant fusions (#48330)
Mirrored from vLLM releases for archival readability. Support the source by reading on the original site.
Signed-off-by: hcenteno [email protected]
(cherry picked from commit 5f8e73c)
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.