Alberto-Codes/turboquant-vllm
TurboQuant KV cache compression plugin for vLLM — asymmetric K/V, 8 models validated, consumer GPUs
⭐ 49
⑂ 7
Python
Apache-2.0
· 2026-04-10推送
49
Watchers
0
贡献者
0
Commits
0
Releases
11
Open Issues
2026-04-10
最近推送
原文
中文
暂无 README