RobTand/gridbook
Out-of-tree vLLM plugin and open format spec for NVFP4-CB / FP8-CB product-codebook weights — 2-6 bit-per-weight LLM quantization served on native Blackwell tensor cores.
⭐ 11
⑂ 3
Python
Apache-2.0
· 1 天前推送
11
Watchers
0
贡献者
0
Commits
0
Releases
1
Open Issues
1 天前
最近推送
原文
中文
暂无 README