Dyluhn/R9V

Working on the fastest vllm path for AMD Radeon AI PRO R9700

Codeberg fork of StillDeadcode / vllm-radiance which is a custom vllm tuned for R9700 GPU's

One line of NInfer for the RTX 3090, RTX 4090 and RTX 5090, consolidated from the forks that carry it: GGUF block formats, ternary Bonsai 2, device route profiles, MTP and DFlash2.

The fastest vLLM build for AMD R9700's. For the latest updates join the Launch80 discord server. I am on X now also https://x.com/bkuyper

The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)

NInfer port for Qwen 3.8 27B on RTX 4090

Qwen3.8-27B on one RTX 4090: full native 262K context via E8 4-bit KV, up to 149 tok/s code decode with MTP3, sm_89-retuned attention prefill, vision, llama.cpp-compatible /metrics + /slots

LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context

Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux builds.