PFlash speculative prefill + TurboQuant KV cache compression for llama.cpp — HIP/ROCm port for AMD RDNA3 (gfx1100)
-
Updated
May 7, 2026 - C++
PFlash speculative prefill + TurboQuant KV cache compression for llama.cpp — HIP/ROCm port for AMD RDNA3 (gfx1100)
Add a description, image, and links to the speculative-decode topic page so that developers can more easily learn about it.
To associate your repository with the speculative-decode topic, visit your repo's landing page and select "manage topics."