# GLM-5 requires transformers with glm_moe_dsa model type support.
# However, the Image rocm/sgl-dev:v0.5.8.post1-rocm720-mi35x-20260219 doesn't provide this support.
python3 -m pip install -U --no-cache-dir \
  "git+https://github.com/huggingface/transformers.git@6ed9ee36f608fd145168377345bfc4a5de12e1e2"

export SGLANG_ROCM_FUSED_DECODE_MLA=0
export ROCM_QUICK_REDUCE_QUANTIZATION=INT4
export SAFETENSORS_FAST_GPU=1

SERVER_LOG=/workspace/server.log
PORT=${PORT:-8888}

# Start GPU monitoring (power, temperature, clocks every second)
start_gpu_monitor

python3 -m sglang.launch_server \
    --model-path $MODEL \
    --host=0.0.0.0 \
    --port $PORT \
    --tensor-parallel-size $TP \
    --trust-remote-code \
    --tool-call-parser glm47 \
    --reasoning-parser glm45 \
    --mem-fraction-static 0.85 \
    --model-loader-extra-config '{"enable_multithread_load": true, "num_threads": 8}' \
    --nsa-prefill-backend tilelang \
    --nsa-decode-backend tilelang > $SERVER_LOG 2>&1 &