SIGN IN SIGN UP

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

0 0 122 Python

[Model] Always use Transformers backend for PaliGemma and Gemma3-MM (#26715)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
C
Cyrus Leung committed
8c017b34908f8d4a877d862dd21b99aef7057c55
Parent: 9c2c228
Committed by GitHub <noreply@github.com> on 10/17/2025, 5:03:35 AM