7d2ed7f05d
- Experiment: experiments/dsv4_h200_vllm_mtp_vs_default/
- Use official DeepSeek-V4 recipe: --speculative-config '{method: mtp, num_speculative_tokens: 1}'
- Reuse default-side results from dsv4_h200_vllm_dspark_vs_default
- Add TTFT analysis for DSpark vs default trade-offs
217 lines
6.8 KiB
Bash
Executable File
217 lines
6.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# vLLM+MTP speculative decoding vs vLLM default comparison on H200.
|
|
# Reuses the default-side results from dsv4_h200_vllm_dspark_vs_default.
|
|
set -Eeuo pipefail
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"
|
|
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/config.env"
|
|
|
|
RUN_ID="${RUN_ID:-$(date '+%Y%m%d-%H%M%S')}"
|
|
RESULT_BASE="${SCRIPT_DIR}/results"
|
|
|
|
log_dir_global="${RESULT_BASE}/${RUN_ID}/logs"
|
|
mkdir -p "$log_dir_global"
|
|
log_init "${log_dir_global}/orchestrator.log"
|
|
|
|
log "experiment=${EXPERIMENT_NAME}"
|
|
log "run_id=${RUN_ID}"
|
|
log "platform=${PLATFORM}"
|
|
log "hardware=${HARDWARE}"
|
|
log "model=${MODEL_PATH}"
|
|
log "spec_method=${SPEC_METHOD}"
|
|
log "spec_tokens=${SPEC_TOKENS}"
|
|
log "default_result_root=${DEFAULT_RESULT_ROOT}"
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Helpers
|
|
# ---------------------------------------------------------------------------
|
|
|
|
is_server_healthy() {
|
|
local port="$1"
|
|
curl --fail --silent --show-error --max-time 5 "http://127.0.0.1:${port}/health" >/dev/null 2>&1
|
|
}
|
|
|
|
stop_server() {
|
|
local pid_file="/data/user1/yy/${EXPERIMENT_NAME}_mtp.pid"
|
|
if [[ -f "$pid_file" ]]; then
|
|
local pid
|
|
pid="$(cat "$pid_file")"
|
|
if kill -0 "$pid" 2>/dev/null; then
|
|
log "stopping mtp server pid=${pid}"
|
|
kill "$pid" 2>/dev/null || true
|
|
sleep 5
|
|
kill -9 "$pid" 2>/dev/null || true
|
|
fi
|
|
rm -f "$pid_file"
|
|
fi
|
|
pkill -9 -f "vllm serve.*DeepSeek-V4-Flash" 2>/dev/null || true
|
|
sleep 2
|
|
}
|
|
|
|
start_server() {
|
|
log "starting mtp server with ${MTP_START_SCRIPT}"
|
|
bash "${MTP_START_SCRIPT}" >> "${log_dir_global}/mtp.server.outer.log" 2>&1
|
|
|
|
if ! is_server_healthy "$MTP_PORT"; then
|
|
log "error: mtp server failed to become healthy"
|
|
return 1
|
|
fi
|
|
log "mtp server is healthy on port ${MTP_PORT}"
|
|
}
|
|
|
|
run_warmup() {
|
|
log "warming up mtp (input=4000, output=512, num=2)"
|
|
"${VENV_CLIENT}/bin/python" "${SCRIPT_DIR}/../../scripts/common/warmup.py" \
|
|
--backend vllm \
|
|
--port "$MTP_PORT" \
|
|
--input-len 4000 \
|
|
--output-len 512 \
|
|
--num 2 \
|
|
--env-python "${VENV_CLIENT}/bin/python" \
|
|
>> "${log_dir_global}/mtp.warmup.log" 2>&1
|
|
log "warmup for mtp completed"
|
|
}
|
|
|
|
scenario_already_completed() {
|
|
local output_file="$1"
|
|
local expected="$2"
|
|
[[ -s "$output_file" ]] || return 1
|
|
local completed
|
|
completed="$(${VENV_CLIENT}/bin/python -c "
|
|
import json, sys
|
|
path = sys.argv[1]
|
|
try:
|
|
with open(path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = line.strip()
|
|
if line:
|
|
data = json.loads(line)
|
|
print(data.get('completed', 0))
|
|
break
|
|
except Exception:
|
|
print(0)
|
|
" "$output_file")"
|
|
[[ "${completed:-0}" -ge "$expected" ]]
|
|
}
|
|
|
|
run_benchmark() {
|
|
local result_root="${RESULT_BASE}/${RUN_ID}/mtp"
|
|
local raw_dir="${result_root}/raw_outputs"
|
|
local bench_log_dir="${result_root}/logs"
|
|
|
|
mkdir -p "$raw_dir" "$bench_log_dir"
|
|
|
|
log "===== mtp BENCHMARK START ====="
|
|
|
|
stop_server
|
|
start_server
|
|
run_warmup
|
|
|
|
for scenario in "${SCENARIOS[@]}"; do
|
|
read -r concurrency input_len output_len num_prompts <<< "$scenario"
|
|
output_file="${raw_dir}/vllm_mtp_$(date '+%m%d')_${concurrency}_${input_len}_${output_len}.jsonl"
|
|
detail_log="${bench_log_dir}/vllm_mtp_c${concurrency}_i${input_len}_o${output_len}.log"
|
|
|
|
if scenario_already_completed "$output_file" "$num_prompts"; then
|
|
log "skipping already-completed mtp scenario: c=${concurrency} i=${input_len} o=${output_len}"
|
|
continue
|
|
fi
|
|
|
|
log "running mtp scenario: c=${concurrency} i=${input_len} o=${output_len} n=${num_prompts}"
|
|
|
|
"${VENV_CLIENT}/bin/python" -m sglang.bench_serving \
|
|
--backend vllm \
|
|
--host 127.0.0.1 \
|
|
--port "$MTP_PORT" \
|
|
--dataset-name random \
|
|
--random-input-len "$input_len" \
|
|
--random-output-len "$output_len" \
|
|
--num-prompts "$num_prompts" \
|
|
--max-concurrency "$concurrency" \
|
|
--request-rate 10000 \
|
|
--output-file "$output_file" \
|
|
--output-details \
|
|
> "$detail_log" 2>&1 || {
|
|
log "ERROR: mtp scenario c=${concurrency} i=${input_len} o=${output_len} failed; see ${detail_log}"
|
|
continue
|
|
}
|
|
|
|
log "finished mtp scenario: output=${output_file}"
|
|
done
|
|
|
|
stop_server
|
|
log "===== mtp BENCHMARK DONE ====="
|
|
}
|
|
|
|
parse_mtp() {
|
|
local result_root="${RESULT_BASE}/${RUN_ID}/mtp"
|
|
log "parsing mtp results in ${result_root}"
|
|
"${VENV_CLIENT}/bin/python" "${SCRIPT_DIR}/../../scripts/common/parse_backend.py" "$result_root" --backend vllm \
|
|
>> "${result_root}/logs/parse.log" 2>&1 || {
|
|
log "WARNING: parser failed for mtp; see ${result_root}/logs/parse.log"
|
|
}
|
|
}
|
|
|
|
write_mtp_metadata() {
|
|
local result_root="${RESULT_BASE}/${RUN_ID}/mtp"
|
|
ensure_result_root "$result_root"
|
|
local meta_json="${result_root}/results.json"
|
|
|
|
local server_args
|
|
server_args="vllm serve $MODEL_PATH --trust-remote-code --tensor-parallel-size $TP --kv-cache-dtype fp8 --max-model-len $MAX_MODEL_LEN --max-num-seqs $MAX_NUM_SEQS --block-size 256 --gpu-memory-utilization 0.90 --tokenizer-mode deepseek_v4 --reasoning-parser deepseek_v4 --speculative-config {\\\"method\\\":\\\"mtp\\\",\\\"num_speculative_tokens\\\":$SPEC_TOKENS} --no-disable-hybrid-kv-cache-manager --disable-uvicorn-access-log --port $MTP_PORT"
|
|
|
|
write_metadata_json \
|
|
"$meta_json" \
|
|
"${EXPERIMENT_NAME}_mtp" \
|
|
"$RUN_ID" \
|
|
"$MODEL_PATH" \
|
|
"vllm" \
|
|
"vllm-mtp" \
|
|
"$HARDWARE" \
|
|
"$ACCELERATOR" \
|
|
"$CHIP" \
|
|
"experiments/${EXPERIMENT_NAME}/run_bench.sh" \
|
|
"$VENV_VLLM" \
|
|
"H200 vLLM+MTP TP=8 benchmark for DeepSeek-V4-Flash"
|
|
|
|
jq --arg server_args "$server_args" \
|
|
'.config = {
|
|
"tp": 8,
|
|
"cuda_visible_devices": "0,1,2,3,4,5,6,7",
|
|
"max_model_len": 32768,
|
|
"max_num_seqs": 256,
|
|
"spec_method": "mtp",
|
|
"spec_tokens": 1,
|
|
"backend": "vllm",
|
|
"server_start_script": "experiments/dsv4_h200_vllm_mtp_vs_default/start_mtp.sh",
|
|
"server_args": $server_args
|
|
}' "$meta_json" > "${meta_json}.tmp" && mv "${meta_json}.tmp" "$meta_json"
|
|
}
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Main
|
|
# ---------------------------------------------------------------------------
|
|
|
|
stop_server
|
|
write_mtp_metadata
|
|
run_benchmark
|
|
parse_mtp
|
|
|
|
log "generating comparison report"
|
|
"${VENV_CLIENT}/bin/python" "${SCRIPT_DIR}/compare.py" \
|
|
--mtp "${RESULT_BASE}/${RUN_ID}/mtp" \
|
|
--default "$DEFAULT_RESULT_ROOT" \
|
|
--output "${RESULT_BASE}/${RUN_ID}/comparison.md" \
|
|
>> "${log_dir_global}/compare.log" 2>&1 || {
|
|
log "WARNING: comparison script failed; see ${log_dir_global}/compare.log"
|
|
}
|
|
|
|
log "all results saved to ${RESULT_BASE}/${RUN_ID}"
|