yy-fighting 3f28edd1a6 feat(p800): add Qwen3-235B-A22B SGLang TP=8 benchmark experiment
Deploy Qwen3-235B-A22B on 8x Kunlun P800 XPU (TP=8) via sglang, adapted
from the proven qwen3-8b launch (attention-backend kunlun, dtype float16,
mem-fraction-static 0.9, XSGL_* XPU env vars). TP bumped to 8 with all 8
/dev/xpu* devices; context-length 8192 (the 8b used 4096 which truncated
2 outputs at 2k+2k).

Patch qwen3_moe.py in the sglang image: load_weights assigned to the
read-only @property routed_experts_weights_of_layer, raising
AttributeError for any qwen3 MoE model (Qwen3-8B is dense, so unaffected).
Fix: assign to the private _routed_experts_weights_of_layer, applied
idempotently in start_server.sh on every start.

bench_serving: isl=2048 osl=2048 concurrency=16 num_prompts=160.
160/160 success in 771s. Summary in results/qwen3_235b_tp8_run1/report.md.
Server on port 30010 (30000 held by the lingering qwen3_8b_bench_tp1).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 06:34:57 +00:00

156 lines
5.5 KiB
Bash
Executable File

#!/usr/bin/env bash
# Orchestrator for the Qwen3-235B-A22B TP=8 benchmark on Kunlun P800.
#
# Flow: write metadata -> start server (start_server.sh) -> warmup+bench_serving
# (isl=2048 osl=2048 c=16 n=160) -> parse results -> report.md.
#
# The bench client (sglang.bench_serving) runs INSIDE the container; results are
# written to a /data1 path that is mounted same-path into the container, so the
# host-side parse_results.py can read them directly.
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"
# Source config.env BEFORE platform.sh so our CONTAINER_NAME default wins
# over the platform's "sglang-dsv4-flash" default (avoids name collisions
# with the dsv4 experiments, which would docker rm -f this container).
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/config.env"
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/../../../scripts/common/platform.sh"
RUN_ID="${RUN_ID:-$(date '+%Y%m%d-%H%M%S')}"
RESULT_ROOT="${RESULT_ROOT:-${SCRIPT_DIR}/results/${RUN_ID}}"
RAW_DIR="${RESULT_ROOT}/raw_outputs"
LOG_DIR="${RESULT_ROOT}/logs"
mkdir -p "$RAW_DIR" "$LOG_DIR"
ensure_result_root "$RESULT_ROOT"
log_init "${LOG_DIR}/orchestrator.log"
log "experiment=${EXPERIMENT_NAME}"
log "run_id=${RUN_ID}"
log "result_root=${RESULT_ROOT}"
log "platform=${PLATFORM} chip=${CHIP} hardware=${HARDWARE}"
log "model=${MODEL_PATH} tp=${TP} backend=${BACKEND}"
log "scenarios=${SCENARIOS[*]}"
# --- metadata --------------------------------------------------------------
METADATA_JSON="${RESULT_ROOT}/results.json"
write_metadata_json \
"$METADATA_JSON" \
"$EXPERIMENT_NAME" \
"$RUN_ID" \
"$MODEL_PATH" \
"$BACKEND" \
"$ENGINE" \
"$HARDWARE" \
"$ACCELERATOR" \
"$CHIP" \
"experiments/${EXPERIMENT_NAME}/run_bench.sh" \
"" \
"Qwen3-235B-A22B SGLang TP=8 benchmark on Kunlun P800 (isl=osl=2048, c=16)"
"${PYTHON:-python3}" - "$METADATA_JSON" "$TP" "$CONTEXT_LENGTH" "$PORT" "$CONTAINER_NAME" "$DOCKER_IMAGE" "$MEM_FRACTION_STATIC" "$DTYPE" "$ATTENTION_BACKEND" <<'PY'
import json, sys
p, tp, ctx, port, cont, img, memfrac, dtype, attn = sys.argv[1:10]
with open(p) as f:
d = json.load(f)
d["config"] = {
"tp": int(tp),
"context_length": int(ctx),
"port": int(port),
"container": cont,
"docker_image": img,
"attention_backend": attn,
"dtype": dtype,
"mem_fraction_static": float(memfrac),
"max_running_requests": 16,
"page_size": 64,
"benchmark": {"input_len": 2048, "output_len": 2048, "concurrency": 16, "num_prompts": 160},
}
with open(p, "w") as f:
json.dump(d, f, indent=2, ensure_ascii=False)
PY
# --- start server (unless caller manages it themselves) --------------------
if [[ -n "${SKIP_MANAGE_SERVER:-}" ]]; then
log "SKIP_MANAGE_SERVER set; assuming server already running on port ${PORT}"
if ! health_check 127.0.0.1 "$PORT" 30; then
log "ERROR: no healthy server at port ${PORT}"
exit 1
fi
else
log "starting server via start_server.sh"
bash "${SCRIPT_DIR}/start_server.sh" >> "${LOG_DIR}/start_server.outer.log" 2>&1
fi
on_exit() {
local code=$?
if [[ -z "${SKIP_MANAGE_SERVER:-}" ]]; then
log "stopping sglang inside ${CONTAINER_NAME} (container kept alive)"
docker exec "$CONTAINER_NAME" bash -lc 'pkill -9 -f sglang.launch_server 2>/dev/null || true' || true
fi
log "orchestrator exiting with code=${code}"
exit "$code"
}
trap on_exit EXIT
# --- run scenarios ---------------------------------------------------------
log "===== BENCHMARK START ====="
for scenario in "${SCENARIOS[@]}"; do
scenario="${scenario//[()]/}"
read -r concurrency input_len output_len num_prompts <<< "$scenario"
today="$(date '+%m%d')"
# Filename convention expected by parse_results.py:
# {chip}_{engine}_{MMDD}_{concurrency}_{input_len}_{output_len}.jsonl
output_file="${RAW_DIR}/${CHIP}_${ENGINE}_${today}_${concurrency}_${input_len}_${output_len}.jsonl"
# parse_results.py reads the human-readable summary from this exact path.
summary_log="${LOG_DIR}/sglang_c${concurrency}_i${input_len}_o${output_len}.log"
log "running scenario: c=${concurrency} i=${input_len} o=${output_len} n=${num_prompts}"
log "output_file=${output_file}"
docker exec "$CONTAINER_NAME" bash -lc "
source /root/miniconda/etc/profile.d/conda.sh
conda activate python310_torch25_cuda
python -m sglang.bench_serving \
--backend ${BACKEND} \
--host 127.0.0.1 \
--port ${PORT} \
--model ${MODEL_PATH} \
--dataset-name random \
--dataset-path ${DATASET_PATH} \
--random-input-len ${input_len} \
--random-output-len ${output_len} \
--random-range-ratio ${RANDOM_RANGE_RATIO} \
--num-prompts ${num_prompts} \
--warmup-requests ${WARMUP} \
--max-concurrency ${concurrency} \
--request-rate ${REQUEST_RATE} \
--output-file ${output_file} \
--output-details \
--seed ${SEED}
" > "$summary_log" 2>&1 || {
log "ERROR: scenario c=${concurrency} i=${input_len} o=${output_len} failed; see ${summary_log}"
tail -60 "$summary_log" 2>/dev/null || true
continue
}
log "finished scenario: output=${output_file}"
log "----- summary -----"
tail -40 "$summary_log" | sed 's/^/ /'
done
log "===== BENCHMARK DONE ====="
log "parsing results..."
"${PYTHON:-python3}" "${SCRIPT_DIR}/parse_results.py" "$RESULT_ROOT" || log "WARNING: parser failed"
log "all results saved to ${RESULT_ROOT}"
log "report: ${RESULT_ROOT}/report.md"