r9700

Here are 7 public repositories matching this topic...

Luce-Org / lucebox

LLM speculative inference server for heterogeneous hardware & consumer GPUs

spark kernel cuda cuda-kernels rocm heterogeneous-computing luce poolside rtx3090 llama-cpp local-ai qwen speculative-decoding strix-halo dflash megakernel speculative-prefill pflash r9700

Updated Sep 15, 2026
C++

GGZ14 / vllm-mxfp4

Star

The fastest vLLM build for dual R9700's. For the latest updates join the Launch80 discord server.

amd intel nvidia vllm localai r9700

Updated Sep 15, 2026
Python

Capicua25x / vllm-rocm-rdna4

Star

vLLM for AMD RDNA4 (gfx1201): Radeon AI PRO R9700 & RX 9070 XT — native MXFP4 linear kernel + spec-decode verify fix, carried as rebased branches (fork-carry model)

amd rocm vllm llm-inference rdna4 mxfp4 gfx1201 r9700

Updated Sep 3, 2026
Python

davidtaylor6130 / InferDeck

Star

App to handle one GPU to multiple models/element with queuing and log tracking all with a local hosted web dashboard

windows ai dashboard queue cpp amd gpu inference model-serving llm local-ai r9700

Updated Sep 15, 2026
C++

hazyumps / flashnext-rocm10-r9700

Star

Experimental ROCm 10 compatibility build for Qwen3.8-Flash-Next on 4x AMD R9700

amd rocm vllm qwen gfx1201 r9700

Updated Sep 8, 2026
Dockerfile

cat5edopeHA / r9v-ai1-deployment

Star

Verified dual-R9700 deployment recipe, configs, scripts, and benchmarks for Dyluhn/R9V Qwen3.8 Flash-Next

amd rocm llm-inference qwen r9700 r9v

Updated Sep 2, 2026
Shell

FA85 / r9700-vllm-rocm72-fixes

Star

Minimal AITER LDS and ROCr idle-CPU fixes for Radeon AI PRO R9700 on vLLM 0.29.0 / ROCm 7.2.3

amd rocm fp8 vllm qwen gfx1201 aiter r9700 radeon-ai-pro-r9700 rocr

Updated Sep 13, 2026
Shell

Add this topic to your repo

To associate your repository with the r9700 topic, visit your repo's landing page and select "manage topics."

Learn more