lna-lab/blackwell-geforce-nvfp4-gemm

NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.

21

Stars

2

Forks

20.7

Radar Score

Declining

Momentum

Scoring Breakdown

Impact13.7

Velocity19.4

Health33.6

Growth Metrics

7-Day Stars

+0

30-Day Stars

+0

Acceleration

x

Language

Python

Why it ranks

Modest but positive momentum.

LLM Frameworks · inference engineTop 97% globally