git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release -j

./build/bin/llama-server \
     -hf bartowski/Qwen3.8-27B-GGUF:Q4_K_M   \
     -hfd incoai/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M   \
     --alias qwen3.8-27b-dflash2   \
     --host 0.0.0.0 \
     --port 8080   \
     --jinja   \
     -ngl 99   \
     -c 262144   \
     --parallel 1   \
     --flash-attn on   \
     --spec-type draft-dflash   \
     --spec-draft-n-max 7   \
     -b 2048 \
     -ub 512   \
     --temp 1.0 \
     --top-p 0.95 \
     --top-k 20 \
     --min-p 0   \
     --chat-template-kwargs '{"reasoning_effort":"medium"}'