SlyBase /
vllm-sly-radiance
Working on the fastest vllm path for AMD Radeon AI PRO R9700
Updated 39 min ago
Why now
Version v1.9.1 came out on October 29.
+12 stars gained this week
Stars gained each day, last 30 days
Usual pace · 3 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
A vLLM Docker image for running Qwen3.8-27B on a single AMD Radeon AI PRO R9700 GPU, with custom MXFP4 kernels and speculative decoding. Aimed at users who want fast local LLM inference on RDNA4 hardware.
Summary written by AI from the repository’s description and README.
SlyBase / vllm-sly-radiance
View on GitHub(opens in new tab)