8652a685e6
- rewrite README with project purpose, standard workflow, corrected index - add docs/NEW_PLATFORM_GUIDE.md (new GPU onboarding SOP, GLM5.2 reuse) - fix ../../scripts/common -> ../../../scripts/common in 42 experiment scripts - refresh stale docs (EXPERIMENT_GUIDE, H200_QUICKSTART, ADAPTIVE_CONCURRENCY_USAGE, BENCHMARK_WORKFLOW) - remove dead code (dp_proxy.py) and .bak leftovers - add p800 adaptive results (tp4_dp2/tp8_dp1 metrics + summary) - gitignore envs/charts and .tmp_charts
117 lines
3.5 KiB
Bash
Executable File
117 lines
3.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
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}/../../../scripts/common/server_docker.sh"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/../../../scripts/common/bench_client_docker.sh"
|
|
# shellcheck source=/dev/null
|
|
source "${SCRIPT_DIR}/config.env"
|
|
|
|
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="${RESULT_ROOT}/logs"
|
|
|
|
ensure_result_root "$RESULT_ROOT"
|
|
log_init "${LOG_DIR}/orchestrator.log"
|
|
|
|
log "experiment=${EXPERIMENT_NAME}"
|
|
log "run_id=${RUN_ID}"
|
|
log "result_root=${RESULT_ROOT}"
|
|
log "platform=${PLATFORM}"
|
|
log "chip=${CHIP}"
|
|
log "accelerator=${ACCELERATOR}"
|
|
log "engine=${ENGINE}"
|
|
log "hardware=${HARDWARE}"
|
|
|
|
# Write initial metadata for this run.
|
|
METADATA_JSON="${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" \
|
|
"" \
|
|
"Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
|
|
|
|
# Start server unless SKIP_MANAGE_SERVER is set.
|
|
if [[ -n "${SKIP_MANAGE_SERVER:-}" ]]; then
|
|
log "SKIP_MANAGE_SERVER is set, assuming server is already running on port ${PORT}"
|
|
if ! health_check 127.0.0.1 "${PORT}" 30; then
|
|
log "ERROR: no healthy server found at port ${PORT}"
|
|
exit 1
|
|
fi
|
|
else
|
|
docker_server_start "${MODEL_PATH}" "${PORT}" "${LOG_DIR}/server.outer.log" "${SERVER_MODE}"
|
|
fi
|
|
|
|
on_exit() {
|
|
local code=$?
|
|
if [[ -z "${SKIP_MANAGE_SERVER:-}" ]]; then
|
|
docker_server_stop
|
|
fi
|
|
log "orchestrator exiting with code=${code}"
|
|
exit "$code"
|
|
}
|
|
trap on_exit EXIT
|
|
|
|
log "===== BENCHMARK START ====="
|
|
|
|
for scenario in "${SCENARIOS[@]}"; do
|
|
# Allow SCENARIOS to be passed as a string like "(32 512 256 160)" from env.
|
|
scenario="${scenario//[()]/}"
|
|
read -r concurrency input_len output_len num_prompts <<< "$scenario"
|
|
# Fallback for legacy 3-field scenarios.
|
|
if [[ -z "${num_prompts:-}" ]]; then
|
|
num_prompts="$NUM_PROMPTS"
|
|
fi
|
|
|
|
tmp_output_file="/tmp/bench_outputs/${CHIP}_${ENGINE}_$(date '+%m%d')_${concurrency}_${input_len}_${output_len}.jsonl"
|
|
host_output_file="${RAW_DIR}/${CHIP}_${ENGINE}_$(date '+%m%d')_${concurrency}_${input_len}_${output_len}.jsonl"
|
|
detail_log="${LOG_DIR}/${BACKEND}_c${concurrency}_i${input_len}_o${output_len}.log"
|
|
|
|
log "running scenario: concurrency=${concurrency} input=${input_len} output=${output_len} num_prompts=${num_prompts}"
|
|
|
|
run_random_case \
|
|
"$BACKEND" \
|
|
"$PORT" \
|
|
"$MODEL_PATH" \
|
|
"$tmp_output_file" \
|
|
"$concurrency" \
|
|
"$input_len" \
|
|
"$output_len" \
|
|
"$num_prompts" \
|
|
"${DATASET_PATH:-}" \
|
|
> "$detail_log" 2>&1 || {
|
|
log "ERROR: scenario c=${concurrency} i=${input_len} o=${output_len} failed"
|
|
continue
|
|
}
|
|
|
|
# Copy the JSONL from the container to the host result directory.
|
|
docker cp "${CONTAINER_NAME}:${tmp_output_file}" "$host_output_file" || {
|
|
log "ERROR: failed to copy ${tmp_output_file} from container"
|
|
continue
|
|
}
|
|
log "finished scenario: output=${host_output_file}"
|
|
done
|
|
|
|
log "===== BENCHMARK DONE ====="
|
|
log "parsing results..."
|
|
"${SCRIPT_DIR}/parse_results.py" "$RESULT_ROOT"
|
|
|
|
log "all results saved to ${RESULT_ROOT}"
|