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] Disable fp8 kv-cache by default for DeepSeek V3.2 (#27121)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
L
Lucas Wilkinson committed
c2bba690658823be5ec6f1742eb10294d4fa2479
Parent: e133d6d
Committed by GitHub <noreply@github.com> on 10/18/2025, 10:05:23 PM