Max Wei CJ

vLLM-2080Ti-Definitive. The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with 100+ tok/s single-request decode with support of FP8 weight

2080Ti-LLM-Toolbox. Single-request LLM serving recipes, patches, and benchmarks for modified RTX 2080 Ti 22GB / SM75 systems

rdna1-gfx101x-rocm-llama-fix. make RDNA1 / Navi1x / gfx101x GPUs (5700XT, W5500 etc.) run modern large language models on ROCm 6 and ROCm 7 through llama.cpp, compatible with modern LLM like Gemma 4 and Qwen3.5, even on a host platform that is not a clean vendor-supported reference system.

ai-proxy-hub. AI Proxy Hub is a cross-platform local gateway for AI clients and upstream APIs. It unifies multiple upstream endpoints behind one local control plane, adds protocol-aware routing and failover, and provides both a Web dashboard and an interactive CLI.

Ragent6. A benchmark for LLM variant quant models at agentic coding situation

M8HeadlessStaging. This is a DIY project to push the Dirtywave M8 Headless into a PCB and make it handheld.