Morph MORPH
SIGN IN SIGN UP
tejas / vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

0 0 122 Python

[Bugfix] Honor --mm_encoder_attn_backend when used (#27124)

Co-authored-by: Bradley D <4551889+bradleyhd@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
B
Bradley D committed
570c3e1cd4b325ee4cb240f9ff74876257cef085
Parent: 3a4255c
Committed by GitHub <noreply@github.com> on 10/23/2025, 12:09:52 PM