new10시간 전· 1 sources
Running Qwen Flash-Next NVFP4 in vLLM: PLE Loading, B12x Fixes, and Stable Inference
Why it matters
Companion code: PLE and B12x compatibility patches, tests, and deployment notes. The repository contains extracted fixes and validation notes, not a complete runtime image. The model loaded. The healt...
1
Sources
+1
24h
—
Growth
1d
Active