sskj/experiments/dsv4_h200_vllm/start_server.sh
Quantong Qiu 8e15ffe1c7 refactor: relocate old docs and add dsv4_h200_vllm experiment
- Move dspark_deepseekv4_fix_pr_prep.md into experiments/dsv4_h200_dspark/
- Move dsv4_inference_comparison_report.md into docs/
- Delete obsolete cleanup_summary.md
- Add experiments/dsv4_h200_vllm/ baseline experiment (envs/vllm + envs/sglang)
2026-07-08 06:19:40 +00:00

66 lines
1.6 KiB
Bash
Executable File

#!/bin/bash
# Start a plain vLLM baseline server for DeepSeek-V4-Flash on H200.
set -e
cd /data/user1/yy
mkdir -p logs
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/config.env"
VENV="${VENV_SERVER}"
export PATH="$VENV/bin:$PATH"
VLLM="$VENV/bin/vllm"
TP=4
LOG="/data/user1/yy/logs/dsv4_h200_vllm_tp${TP}_$(date +%Y%m%d_%H%M%S).log"
PID_FILE="/data/user1/yy/dsv4_h200_vllm.pid"
export TMPDIR=/data/user1/yy/tmp
export CUDA_VISIBLE_DEVICES=4,5,6,7
echo "=== Starting DeepSeek-V4-Flash vLLM baseline (TP=$TP) ==="
echo "Model: $MODEL_PATH"
echo "Port: $PORT"
echo "Log: $LOG"
rm -f "$PID_FILE"
nohup "$VLLM" serve "$MODEL_PATH" \
--trust-remote-code \
--tensor-parallel-size "$TP" \
--kv-cache-dtype fp8 \
--block-size 256 \
--max-model-len auto \
--max-num-seqs 256 \
--gpu-memory-utilization 0.90 \
--tokenizer-mode deepseek_v4 \
--reasoning-parser deepseek_v4 \
--no-disable-hybrid-kv-cache-manager \
--disable-uvicorn-access-log \
--port "$PORT" \
> "$LOG" 2>&1 &
PID=$!
echo $PID > "$PID_FILE"
echo "PID: $PID"
echo "Waiting for health..."
for i in $(seq 1 240); do
if curl -s "http://127.0.0.1:$PORT/health" > /dev/null 2>&1; then
echo "Server is ready at http://127.0.0.1:$PORT"
echo "Log: $LOG"
exit 0
fi
if ! kill -0 $PID 2>/dev/null; then
echo "ERROR: Server exited early"
tail -200 "$LOG"
exit 1
fi
echo "Waiting... ($i/240)"
sleep 5
done
echo "ERROR: Server not healthy after 240 retries"
tail -200 "$LOG"
exit 1