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
67 lines
2.0 KiB
Bash
Executable File
67 lines
2.0 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# H200 native vllm-dspark benchmark orchestrator.
|
|
# This wraps the legacy scripts/benchmark_dspark_0707/ grid benchmark so that
|
|
# results live under experiments/dsv4_h200_dspark/results/<RUN_ID>/.
|
|
|
|
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_ROOT="${RESULT_ROOT:-${SCRIPT_DIR}/results/${RUN_ID}}"
|
|
LOG_DIR="${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}"
|
|
log "model=${MODEL_PATH}"
|
|
log "server_start_script=${SERVER_START_SCRIPT}"
|
|
|
|
# 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/${EXPERIMENT_NAME}/run_bench.sh" \
|
|
"$VENV_SERVER" \
|
|
"H200 native vllm-dspark benchmark for DeepSeek-V4-Flash-DSpark"
|
|
|
|
log "starting legacy DSpark grid benchmark"
|
|
RUN_ID="$RUN_ID" \
|
|
RESULT_ROOT="$RESULT_ROOT" \
|
|
PORT="$PORT" \
|
|
MODEL_PATH="$MODEL_PATH" \
|
|
SERVER_START_SCRIPT="$SERVER_START_SCRIPT" \
|
|
SKIP_MANAGE_SERVER="${SKIP_MANAGE_SERVER:-}" \
|
|
bash "$LEGACY_GRID_SCRIPT" >> "${LOG_DIR}/legacy_grid.log" 2>&1
|
|
|
|
log "parsing results"
|
|
"$VENV_CLIENT/bin/python" "$LEGACY_PARSE_SCRIPT" "$RESULT_ROOT" >> "${LOG_DIR}/parse.log" 2>&1 || {
|
|
log "WARNING: legacy parser failed; see ${LOG_DIR}/parse.log"
|
|
}
|
|
|
|
log "all results saved to ${RESULT_ROOT}"
|