peonist-ai

Githubhttps://peonist.aiFollowers 7

代码库

peonist-ai/halogen-flash-server

137

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

Shell

amdgfx1151gpu-inferencehipinference-enginellmllm-servinglocal-llmlong-contextmixture-of-expertsopenai-apiqwenqwen3radeonrocmryzen-aispeculative-decodingstrix-halo