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] Fix broken MTP weight loading for FP8 KV Scales (#27227)

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
B
Benjamin Chislett committed
f381cf2302460fb921d67fc1356b9d1b1a93e960
Parent: 5ff5d94
Committed by GitHub <noreply@github.com> on 10/21/2025, 5:51:44 AM