feat: add run_bench.sh and fix config for dsv4_pro6000_sglang_tp_dp_matrix
- Migrate run_bench.sh from dsv4_h200_sglang_tp_dp_matrix - Add missing generate_scenarios.py, compare.py, matrix.json - Fix MODEL_PATH to /root/data/models/ds_flash_v4 - Fix DATASET_PATH to local dummy_sharegpt.json - Tune CONTEXT_LENGTH, MAX_RUNNING_REQUESTS, MEM_FRACTION_STATIC for RTX 6000D 83GB - Exclude GPU 2 due to DRAM Uncorrectable ECC hardware error
This commit is contained in:
Root
parent
819850c4a1
commit
a7f453b997
162
experiments/dsv4_pro6000_sglang_tp_dp_matrix/compare.py
Executable file
162
experiments/dsv4_pro6000_sglang_tp_dp_matrix/compare.py
Executable file
@ -0,0 +1,162 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Cross TP×DP configuration comparison for dsv4_h200_sglang_tp_dp_matrix.
|
||||
|
||||
Usage:
|
||||
python3 compare.py --run-root results/<run_id> [--output comparison.md]
|
||||
"""
|
||||
import argparse
|
||||
import json
|
||||
import re
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def load_result(result_root: Path) -> dict:
|
||||
path = result_root / "results.json"
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
|
||||
|
||||
def slo_status(ttft_p95_ms: float, tpot_mean_ms: float,
|
||||
ttft_limit_ms: float = 3000.0, tpot_limit_ms: float = 50.0) -> str:
|
||||
ttft_ok = ttft_p95_ms < ttft_limit_ms
|
||||
tpot_ok = tpot_mean_ms < tpot_limit_ms
|
||||
if ttft_ok and tpot_ok:
|
||||
return "PASS"
|
||||
if ttft_ok or tpot_ok:
|
||||
return "PARTIAL"
|
||||
return "FAIL"
|
||||
|
||||
|
||||
def gpu_memory_str(gpu: dict | None) -> str:
|
||||
if not gpu:
|
||||
return "-"
|
||||
peak = gpu.get("peak_used_mb", 0)
|
||||
total = gpu.get("memory_total_mb", 0)
|
||||
if total:
|
||||
return f"{peak:.0f}/{total:.0f} ({100*peak/total:.1f}%)"
|
||||
return f"{peak:.0f}"
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--run-root", type=Path, required=True)
|
||||
parser.add_argument("-o", "--output", type=Path, default=Path("comparison.md"))
|
||||
parser.add_argument("--ttft-limit", type=float, default=3000.0)
|
||||
parser.add_argument("--tpot-limit", type=float, default=50.0)
|
||||
args = parser.parse_args()
|
||||
|
||||
# Discover configurations: tp*_dp* directories.
|
||||
configs = []
|
||||
for subdir in sorted(args.run_root.iterdir()):
|
||||
if not subdir.is_dir():
|
||||
continue
|
||||
name = subdir.name
|
||||
if not (name.startswith("tp") and "_dp" in name):
|
||||
continue
|
||||
results_json = subdir / "results.json"
|
||||
if not results_json.exists():
|
||||
continue
|
||||
configs.append((name, load_result(subdir)))
|
||||
|
||||
if not configs:
|
||||
print(f"No tp*_dp* results found under {args.run_root}")
|
||||
return
|
||||
|
||||
model = configs[0][1].get("metadata", {}).get("model", "unknown")
|
||||
hardware = configs[0][1].get("metadata", {}).get("hardware", "unknown")
|
||||
|
||||
# Group by scenario name.
|
||||
by_scenario: dict[str, dict[str, dict]] = defaultdict(dict)
|
||||
skipped: dict[str, dict[str, str]] = defaultdict(dict)
|
||||
for label, data in configs:
|
||||
for s in data.get("scenarios", []):
|
||||
key = s["name"]
|
||||
if s.get("status") == "skipped_oom":
|
||||
skipped[key][label] = s.get("note", "skipped")
|
||||
else:
|
||||
by_scenario[key][label] = s
|
||||
|
||||
with open(args.output, "w", encoding="utf-8") as f:
|
||||
f.write(f"# SGLang TP×DP matrix comparison ({hardware})\n\n")
|
||||
f.write("## Summary\n\n")
|
||||
f.write(f"- Model: `{model}`\n")
|
||||
f.write(f"- Hardware: {hardware}\n")
|
||||
f.write("- Backend: SGLang (Docker)\n")
|
||||
f.write("- Benchmark client: `sglang.bench_serving`\n")
|
||||
f.write(f"- SLO reference: TTFT P95 < {args.ttft_limit}ms, TPOT mean < {args.tpot_limit}ms\n\n")
|
||||
|
||||
# Configuration overview.
|
||||
f.write("### Configurations\n\n")
|
||||
f.write("| Config | TP | DP | GPUs/replica | Notes |\n")
|
||||
f.write("|---|---:|---:|---:|---|\n")
|
||||
for label, data in configs:
|
||||
cfg = data.get("config", {})
|
||||
tp = cfg.get("tp", "?")
|
||||
dp = cfg.get("dp", "?")
|
||||
f.write(f"| {label} | {tp} | {dp} | {tp} | server args recorded per ISL in results.json |\n")
|
||||
f.write("\n")
|
||||
|
||||
# Side-by-side table.
|
||||
f.write("## Side-by-side results\n\n")
|
||||
headers = [
|
||||
"Scenario", "ISL", "DSL", "Config", "Conc", "Req/s", "OutTok/s",
|
||||
"TTFT P95(ms)", "TTFT P99(ms)", "TPOT Mean(ms)", "TPOT P95(ms)",
|
||||
"TPOT P99(ms)", "E2E P99(ms)", "Peak GPU mem", "SLO"
|
||||
]
|
||||
f.write("| " + " | ".join(headers) + " |\n")
|
||||
f.write("|" + "|".join(["---"] * len(headers)) + "|\n")
|
||||
|
||||
for scenario_name in sorted(by_scenario.keys(), key=lambda x: tuple(map(int, re.findall(r"\d+", x)))):
|
||||
_, isl, dsl = re.findall(r"\d+", scenario_name)
|
||||
for label, data in configs:
|
||||
s = by_scenario[scenario_name].get(label)
|
||||
if s is None:
|
||||
if scenario_name in skipped and label in skipped[scenario_name]:
|
||||
note = skipped[scenario_name][label]
|
||||
f.write(f"| {scenario_name} | {isl} | {dsl} | {label} | - | - | - | - | - | - | - | - | - | - | {note} |\n")
|
||||
continue
|
||||
cfg = s["config"]
|
||||
m = s["metrics"]
|
||||
status = slo_status(m["ttft_ms"]["p95"], m["tpot_ms"]["mean"], args.ttft_limit, args.tpot_limit)
|
||||
gpu = m.get("gpu_memory")
|
||||
f.write(
|
||||
f"| {scenario_name} | {isl} | {dsl} | {label} | {cfg['concurrency']} | "
|
||||
f"{m['request_throughput']:.2f} | {m['output_token_throughput']:.2f} | "
|
||||
f"{m['ttft_ms']['p95']:.2f} | {m['ttft_ms']['p99']:.2f} | "
|
||||
f"{m['tpot_ms']['mean']:.2f} | {m['tpot_ms']['p95']:.2f} | {m['tpot_ms']['p99']:.2f} | "
|
||||
f"{m['e2e_ms']['p99']:.2f} | {gpu_memory_str(gpu)} | {status} |\n"
|
||||
)
|
||||
|
||||
# Best throughput per ISL/DSL.
|
||||
f.write("\n## Best throughput per (ISL, DSL)\n\n")
|
||||
f.write("| ISL | DSL | Best Config | Concurrency | OutTok/s | TTFT P95(ms) | TPOT Mean(ms) | SLO |\n")
|
||||
f.write("|---:|---:|---|---:|---:|---:|---:|---:|\n")
|
||||
best_by_shape: dict[tuple[int, int], tuple[float, str, dict]] = {}
|
||||
for scenario_name, backends in by_scenario.items():
|
||||
_, isl, dsl = re.findall(r"\d+", scenario_name)
|
||||
isl_i, dsl_i = int(isl), int(dsl)
|
||||
for label, s in backends.items():
|
||||
m = s["metrics"]
|
||||
out_tok = m["output_token_throughput"]
|
||||
if (isl_i, dsl_i) not in best_by_shape or out_tok > best_by_shape[(isl_i, dsl_i)][0]:
|
||||
best_by_shape[(isl_i, dsl_i)] = (out_tok, label, s)
|
||||
for (isl_i, dsl_i), (out_tok, label, s) in sorted(best_by_shape.items()):
|
||||
m = s["metrics"]
|
||||
status = slo_status(m["ttft_ms"]["p95"], m["tpot_ms"]["mean"], args.ttft_limit, args.tpot_limit)
|
||||
f.write(
|
||||
f"| {isl_i} | {dsl_i} | {label} | {s['config']['concurrency']} | "
|
||||
f"{out_tok:.2f} | {m['ttft_ms']['p95']:.2f} | {m['tpot_ms']['mean']:.2f} | {status} |\n"
|
||||
)
|
||||
|
||||
f.write("\n## Notes\n\n")
|
||||
f.write("- SLO check uses TTFT P95 and TPOT mean.\n")
|
||||
f.write("- A PARTIAL indicates one of the two metrics is out of target; FAIL indicates both are out.\n")
|
||||
f.write("- `Peak GPU mem` shows peak used / total MB and utilization percentage.\n")
|
||||
f.write("- Optional (P) combinations that failed are marked as skipped/OOM and do not break the run.\n")
|
||||
|
||||
print(f"Wrote comparison to {args.output}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@ -7,7 +7,7 @@
|
||||
|
||||
EXPERIMENT="dsv4_pro6000_sglang_tp_dp_matrix"
|
||||
MODEL_NAME="DeepSeek-V4-Flash"
|
||||
MODEL_PATH="/data/hf_models/DeepSeek-V4-Flash"
|
||||
MODEL_PATH="/root/data/models/ds_flash_v4"
|
||||
SERVED_MODEL_NAME="deepseek-v4-flash"
|
||||
|
||||
SGLANG_PORT="${SGLANG_PORT:-30031}"
|
||||
@ -20,7 +20,7 @@ VENV_CLIENT="${VENV_CLIENT:-/root/.miniconda3/envs/sglang}"
|
||||
# Run the benchmark client natively (0) or inside Docker (1).
|
||||
USE_DOCKER_CLIENT="${USE_DOCKER_CLIENT:-1}"
|
||||
|
||||
export CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES:-0,1,2,3,4,5,6,7}"
|
||||
export CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES:-0,1,3,4,5,6,7}"
|
||||
|
||||
# Runtime working directory for logs, pid files, and tmp. Defaults to a local
|
||||
# directory under this experiment so the benchmark is self-contained.
|
||||
@ -33,10 +33,10 @@ declare -a PARALLEL_CONFIGS=(
|
||||
"8 1"
|
||||
)
|
||||
|
||||
# SGLang server settings
|
||||
CONTEXT_LENGTH="${CONTEXT_LENGTH:-1048576}"
|
||||
MAX_RUNNING_REQUESTS="${MAX_RUNNING_REQUESTS:-128}"
|
||||
MEM_FRACTION_STATIC="${MEM_FRACTION_STATIC:-0.88}"
|
||||
# SGLang server settings (tuned for RTX 6000D 83GB)
|
||||
CONTEXT_LENGTH="${CONTEXT_LENGTH:-262144}"
|
||||
MAX_RUNNING_REQUESTS="${MAX_RUNNING_REQUESTS:-32}"
|
||||
MEM_FRACTION_STATIC="${MEM_FRACTION_STATIC:-0.80}"
|
||||
MOE_RUNNER_BACKEND="${MOE_RUNNER_BACKEND:-marlin}"
|
||||
|
||||
# Deployment switch. 0 = native sglang venv, 1 = Docker.
|
||||
@ -46,7 +46,7 @@ DOCKER_IMAGE="${DOCKER_IMAGE:-lmsysorg/sglang:latest}"
|
||||
# Dataset used by sglang.bench_serving --dataset-name random.
|
||||
# The random sampler needs a ShareGPT-style JSON file locally; it falls back to
|
||||
# downloading from HuggingFace, which usually fails on offline nodes.
|
||||
DATASET_PATH="${DATASET_PATH:-/data/yy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json}"
|
||||
DATASET_PATH="${DATASET_PATH:-/root/data/yy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json}"
|
||||
|
||||
# Matrix and concurrency rules are defined in matrix.json by default.
|
||||
MATRIX_FILE="${MATRIX_FILE:-${SCRIPT_DIR:-.}/matrix.json}"
|
||||
|
||||
98
experiments/dsv4_pro6000_sglang_tp_dp_matrix/generate_scenarios.py
Executable file
98
experiments/dsv4_pro6000_sglang_tp_dp_matrix/generate_scenarios.py
Executable file
@ -0,0 +1,98 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Generate the scenario list for the TP×DP matrix experiment.
|
||||
|
||||
Reads matrix.json and prints TSV lines:
|
||||
|
||||
mark input_len output_len concurrency num_prompts
|
||||
|
||||
mark is one of Y/P/N. The caller (run_bench.sh) decides how to treat each.
|
||||
"""
|
||||
import argparse
|
||||
import json
|
||||
import math
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def sample_concurrency(low: int, high: int, target: int) -> list[int]:
|
||||
"""Return only the low and high concurrency values in [low, high].
|
||||
|
||||
For the TP×DP matrix we only need the two endpoints of the concurrency
|
||||
range (e.g. 1 and 128 for ISL=1024). The `target` argument is kept for
|
||||
API compatibility but is ignored.
|
||||
"""
|
||||
assert 1 <= low <= high, f"invalid concurrency range: {low}-{high}"
|
||||
if low == high:
|
||||
return [low]
|
||||
return [low, high]
|
||||
|
||||
|
||||
def generate_scenarios(matrix_path: Path, mode: str, target_samples: int) -> list[dict]:
|
||||
with open(matrix_path, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
|
||||
matrix = data["matrix"]
|
||||
concurrency_cfg = data["concurrency"]
|
||||
|
||||
scenarios = []
|
||||
for isl_str in sorted(matrix.keys(), key=int):
|
||||
dsl_map = matrix[isl_str]
|
||||
low = concurrency_cfg[isl_str]["low"]
|
||||
high = concurrency_cfg[isl_str]["high"]
|
||||
concurrencies = sample_concurrency(low, high, target_samples)
|
||||
|
||||
for dsl_str in sorted(dsl_map.keys(), key=int):
|
||||
mark = dsl_map[dsl_str]
|
||||
if mode == "Y" and mark != "Y":
|
||||
continue
|
||||
if mode == "Y+P" and mark not in ("Y", "P"):
|
||||
continue
|
||||
# mode == "all" keeps everything, including N.
|
||||
|
||||
for conc in concurrencies:
|
||||
scenarios.append(
|
||||
{
|
||||
"mark": mark,
|
||||
"input_len": int(isl_str),
|
||||
"output_len": int(dsl_str),
|
||||
"concurrency": conc,
|
||||
"num_prompts": conc * 5,
|
||||
}
|
||||
)
|
||||
|
||||
return scenarios
|
||||
|
||||
|
||||
def main() -> None:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--matrix", type=Path, default=Path("matrix.json"))
|
||||
parser.add_argument("--mode", choices=["Y", "Y+P", "all"], default=None,
|
||||
help="Scenario selection mode. Defaults to matrix.mode.")
|
||||
parser.add_argument("--target-samples", type=int, default=0,
|
||||
help="Target number of concurrency samples. 0 = heuristic (6-8).")
|
||||
args = parser.parse_args()
|
||||
|
||||
with open(args.matrix, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
|
||||
mode = args.mode if args.mode else data.get("mode", "Y+P")
|
||||
|
||||
target_samples = args.target_samples
|
||||
if target_samples <= 0:
|
||||
env_samples = os.getenv("CONCURRENCY_SAMPLES", "0")
|
||||
try:
|
||||
target_samples = int(env_samples)
|
||||
except ValueError:
|
||||
target_samples = 0
|
||||
if target_samples <= 0:
|
||||
target_samples = 7
|
||||
|
||||
scenarios = generate_scenarios(args.matrix, mode, target_samples)
|
||||
|
||||
print("mark\tinput_len\toutput_len\tconcurrency\tnum_prompts")
|
||||
for s in scenarios:
|
||||
print(f"{s['mark']}\t{s['input_len']}\t{s['output_len']}\t{s['concurrency']}\t{s['num_prompts']}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
81
experiments/dsv4_pro6000_sglang_tp_dp_matrix/matrix.json
Normal file
81
experiments/dsv4_pro6000_sglang_tp_dp_matrix/matrix.json
Normal file
@ -0,0 +1,81 @@
|
||||
{
|
||||
"comment": "ISL/DSL matrix for dsv4_h200_sglang_tp_dp_matrix. Y=must test, P=optional (record N on failure), N=skip.",
|
||||
"mode": "Y",
|
||||
"comment": "Only mandatory (Y) combinations are tested; 1M ISL is excluded per user request.",
|
||||
"matrix": {
|
||||
"1024": {
|
||||
"128": "Y",
|
||||
"256": "Y",
|
||||
"512": "Y",
|
||||
"1024": "Y",
|
||||
"2048": "Y",
|
||||
"4096": "Y"
|
||||
},
|
||||
"4096": {
|
||||
"128": "Y",
|
||||
"256": "Y",
|
||||
"512": "Y",
|
||||
"1024": "Y",
|
||||
"2048": "Y",
|
||||
"4096": "Y"
|
||||
},
|
||||
"16384": {
|
||||
"128": "Y",
|
||||
"256": "Y",
|
||||
"512": "Y",
|
||||
"1024": "Y",
|
||||
"2048": "Y",
|
||||
"4096": "P"
|
||||
},
|
||||
"65536": {
|
||||
"128": "Y",
|
||||
"256": "Y",
|
||||
"512": "Y",
|
||||
"1024": "Y",
|
||||
"2048": "P",
|
||||
"4096": "N"
|
||||
},
|
||||
"131072": {
|
||||
"128": "Y",
|
||||
"256": "Y",
|
||||
"512": "Y",
|
||||
"1024": "P",
|
||||
"2048": "N",
|
||||
"4096": "N"
|
||||
},
|
||||
"262144": {
|
||||
"128": "Y",
|
||||
"256": "Y",
|
||||
"512": "P",
|
||||
"1024": "N",
|
||||
"2048": "N",
|
||||
"4096": "N"
|
||||
},
|
||||
"524288": {
|
||||
"128": "Y",
|
||||
"256": "P",
|
||||
"512": "N",
|
||||
"1024": "N",
|
||||
"2048": "N",
|
||||
"4096": "N"
|
||||
},
|
||||
"1048576": {
|
||||
"128": "Y",
|
||||
"256": "P",
|
||||
"512": "N",
|
||||
"1024": "N",
|
||||
"2048": "N",
|
||||
"4096": "N"
|
||||
}
|
||||
},
|
||||
"concurrency": {
|
||||
"1024": { "low": 1, "high": 128 },
|
||||
"4096": { "low": 1, "high": 64 },
|
||||
"16384": { "low": 1, "high": 32 },
|
||||
"65536": { "low": 1, "high": 8 },
|
||||
"131072": { "low": 1, "high": 4 },
|
||||
"262144": { "low": 1, "high": 2 },
|
||||
"524288": { "low": 1, "high": 2 },
|
||||
"1048576": { "low": 1, "high": 2 }
|
||||
}
|
||||
}
|
||||
558
experiments/dsv4_pro6000_sglang_tp_dp_matrix/run_bench.sh
Executable file
558
experiments/dsv4_pro6000_sglang_tp_dp_matrix/run_bench.sh
Executable file
@ -0,0 +1,558 @@
|
||||
#!/usr/bin/env bash
|
||||
# TP×DP matrix benchmark for DeepSeek-V4-Flash on SGLang (Docker).
|
||||
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"
|
||||
MATRIX_FILE="${MATRIX_FILE:-${SCRIPT_DIR}/matrix.json}"
|
||||
MATRIX_MODE="${MATRIX_MODE:-Y}"
|
||||
SCENARIO_TIMEOUT_S="${SCENARIO_TIMEOUT_S:-1800}"
|
||||
GPU_MEM_SAMPLE_INTERVAL_S="${GPU_MEM_SAMPLE_INTERVAL_S:-1}"
|
||||
DRY_RUN="${DRY_RUN:-0}"
|
||||
GRID_LIMIT="${GRID_LIMIT:-0}"
|
||||
|
||||
# Export variables used inside functions that are called via bash -c subshells.
|
||||
export DATASET_PATH MODEL_PATH RESULT_BASE DOCKER_IMAGE USE_DOCKER_CLIENT
|
||||
|
||||
if [[ -x "${VENV_CLIENT}/bin/python" ]]; then
|
||||
PYTHON="${VENV_CLIENT}/bin/python"
|
||||
else
|
||||
PYTHON="$(command -v python3)"
|
||||
fi
|
||||
|
||||
DOCKER_IMAGE="${DOCKER_IMAGE:-lmsysorg/sglang:latest}"
|
||||
|
||||
log_dir_global="${RESULT_BASE}/${RUN_ID}/logs"
|
||||
mkdir -p "$log_dir_global"
|
||||
log_init "${log_dir_global}/orchestrator.log"
|
||||
|
||||
log "experiment=${EXPERIMENT_NAME} run_id=${RUN_ID} platform=${PLATFORM} hardware=${HARDWARE}"
|
||||
log "matrix_mode=${MATRIX_MODE} matrix_file=${MATRIX_FILE} dry_run=${DRY_RUN} grid_limit=${GRID_LIMIT}"
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Helpers
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
is_server_healthy() {
|
||||
curl --fail --silent --show-error --max-time 5 "http://127.0.0.1:${SGLANG_PORT}/health" >/dev/null 2>&1
|
||||
}
|
||||
|
||||
stop_server() {
|
||||
local tp="$1"
|
||||
local dp="$2"
|
||||
|
||||
local pid_file="${RUNTIME_BASE}/${EXPERIMENT}_sglang_tp${tp}_dp${dp}.pid"
|
||||
if [[ -f "$pid_file" ]]; then
|
||||
local pid
|
||||
pid="$(cat "$pid_file")"
|
||||
# In container-reuse mode, pid is the server PID inside the container.
|
||||
if [[ -n "${CONTAINER_NAME:-}" ]]; then
|
||||
if docker exec "$CONTAINER_NAME" kill -0 "$pid" 2>/dev/null; then
|
||||
log "stopping sglang server inside container (tp=${tp}, dp=${dp}, pid=${pid})"
|
||||
docker exec "$CONTAINER_NAME" kill "$pid" 2>/dev/null || true
|
||||
sleep 5
|
||||
docker exec "$CONTAINER_NAME" kill -9 "$pid" 2>/dev/null || true
|
||||
fi
|
||||
else
|
||||
if kill -0 "$pid" 2>/dev/null; then
|
||||
log "stopping sglang server pid=${pid} (tp=${tp}, dp=${dp})"
|
||||
kill "$pid" 2>/dev/null || true
|
||||
sleep 5
|
||||
kill -9 "$pid" 2>/dev/null || true
|
||||
fi
|
||||
fi
|
||||
rm -f "$pid_file"
|
||||
fi
|
||||
|
||||
# Fallback: remove any Docker container started by this experiment (legacy mode).
|
||||
if [[ -z "${CONTAINER_NAME:-}" ]]; then
|
||||
docker rm -f "${EXPERIMENT}_sglang_tp${tp}_dp${dp}" >/dev/null 2>&1 || true
|
||||
fi
|
||||
|
||||
# Fallback: kill any sglang serve processes for this model.
|
||||
pkill -9 -f "sglang serve.*${MODEL_NAME}" 2>/dev/null || true
|
||||
pkill -9 -f "sglang serve.*${MODEL_PATH}" 2>/dev/null || true
|
||||
sleep 2
|
||||
}
|
||||
|
||||
build_server_args() {
|
||||
local tp="$1"
|
||||
local dp="$2"
|
||||
|
||||
local args=(
|
||||
"sglang serve" "$MODEL_PATH"
|
||||
--trust-remote-code
|
||||
--tp-size "$tp"
|
||||
--moe-runner-backend "$MOE_RUNNER_BACKEND"
|
||||
--context-length "$CONTEXT_LENGTH"
|
||||
--max-running-requests "$MAX_RUNNING_REQUESTS"
|
||||
--mem-fraction-static "$MEM_FRACTION_STATIC"
|
||||
--host 0.0.0.0
|
||||
--port "$SGLANG_PORT"
|
||||
)
|
||||
if [[ "$dp" -gt 1 ]]; then
|
||||
args+=(
|
||||
--dp-size "$dp"
|
||||
)
|
||||
fi
|
||||
printf '%s ' "${args[@]}"
|
||||
}
|
||||
|
||||
start_server() {
|
||||
local tp="$1"
|
||||
local dp="$2"
|
||||
|
||||
log "starting sglang server tp=${tp} dp=${dp}"
|
||||
if [[ -n "${CONTAINER_NAME:-}" ]]; then
|
||||
bash "${SCRIPT_DIR}/run_sglang_in_container.sh" "$tp" "$dp" \
|
||||
>> "${log_dir_global}/sglang_tp${tp}_dp${dp}.server.outer.log" 2>&1
|
||||
else
|
||||
bash "${SCRIPT_DIR}/start_sglang_dp.sh" "$tp" "$dp" \
|
||||
>> "${log_dir_global}/sglang_tp${tp}_dp${dp}.server.outer.log" 2>&1
|
||||
fi
|
||||
|
||||
if ! is_server_healthy; then
|
||||
log "error: sglang server tp=${tp} dp=${dp} failed health check on port ${SGLANG_PORT}"
|
||||
return 1
|
||||
fi
|
||||
log "sglang server tp=${tp} dp=${dp} is healthy on port ${SGLANG_PORT}"
|
||||
}
|
||||
|
||||
restart_server() {
|
||||
local tp="$1"
|
||||
local dp="$2"
|
||||
log "restarting sglang server tp=${tp} dp=${dp} after non-OOM failure"
|
||||
stop_server "$tp" "$dp"
|
||||
sleep 10
|
||||
start_server "$tp" "$dp"
|
||||
}
|
||||
|
||||
run_bench_serving() {
|
||||
# Run sglang.bench_serving either natively or inside the SGLang Docker image.
|
||||
if [[ "${USE_DOCKER_CLIENT:-1}" == "1" ]]; then
|
||||
local vol_args=()
|
||||
vol_args+=("-v" "${MODEL_PATH}:${MODEL_PATH}:ro")
|
||||
if [[ -n "${DATASET_PATH:-}" ]]; then
|
||||
vol_args+=("-v" "${DATASET_PATH}:${DATASET_PATH}:ro")
|
||||
fi
|
||||
vol_args+=("-v" "${RESULT_BASE}:${RESULT_BASE}")
|
||||
docker run --rm \
|
||||
--network host \
|
||||
"${vol_args[@]}" \
|
||||
-e PYTHONUNBUFFERED=1 \
|
||||
"${DOCKER_IMAGE}" \
|
||||
python -m sglang.bench_serving "$@"
|
||||
else
|
||||
"$PYTHON" -m sglang.bench_serving "$@"
|
||||
fi
|
||||
}
|
||||
export -f run_bench_serving
|
||||
|
||||
run_warmup() {
|
||||
local input_len="$1"
|
||||
local output_len="$2"
|
||||
|
||||
log "warming up (input=${input_len}, output=${output_len}, num=1)"
|
||||
bash -c '
|
||||
run_bench_serving \
|
||||
--backend sglang \
|
||||
--host 127.0.0.1 \
|
||||
--port "'"$SGLANG_PORT"'" \
|
||||
--dataset-name random \
|
||||
--dataset-path "'"$DATASET_PATH"'" \
|
||||
--random-input-len "'"$input_len"'" \
|
||||
--random-output-len "'"$output_len"'" \
|
||||
--num-prompts 1 \
|
||||
--max-concurrency 1 \
|
||||
--request-rate 10000 \
|
||||
--output-file /dev/null \
|
||||
--output-details \
|
||||
>> "'"${log_dir_global}/warmup.log"'" 2>&1
|
||||
'
|
||||
log "warmup completed"
|
||||
}
|
||||
|
||||
scenario_already_completed() {
|
||||
local output_file="$1"
|
||||
local expected="$2"
|
||||
[[ -s "$output_file" ]] || return 1
|
||||
local completed
|
||||
completed="$("$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" ]]
|
||||
}
|
||||
|
||||
scenario_already_processed() {
|
||||
local result_root="$1"
|
||||
local scenario_name="$2"
|
||||
local json_path="${result_root}/results.json"
|
||||
[[ -f "$json_path" ]] || return 1
|
||||
"$PYTHON" -c "
|
||||
import json, sys
|
||||
path, name = sys.argv[1], sys.argv[2]
|
||||
try:
|
||||
with open(path, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
for s in data.get('scenarios', []):
|
||||
if s.get('name') == name:
|
||||
if s.get('status') or s.get('metrics', {}).get('success', 0) > 0:
|
||||
sys.exit(0)
|
||||
except Exception:
|
||||
pass
|
||||
sys.exit(1)
|
||||
" "$json_path" "$scenario_name"
|
||||
}
|
||||
|
||||
detect_oom() {
|
||||
local detail_log="$1"
|
||||
local server_outer_log="$2"
|
||||
local pattern='CUDA out of memory|torch\.OutOfMemoryError|OutOfMemory|out of memory|OOM|RESOURCE_EXHAUSTED|Failed to allocate memory'
|
||||
if grep -Eiq "$pattern" "$detail_log" "$server_outer_log" 2>/dev/null; then
|
||||
return 0
|
||||
fi
|
||||
return 1
|
||||
}
|
||||
|
||||
start_gpu_monitor() {
|
||||
local csv_path="$1"
|
||||
mkdir -p "$(dirname "$csv_path")"
|
||||
nvidia-smi \
|
||||
--query-gpu=timestamp,index,memory.used,memory.total,utilization.gpu \
|
||||
--format=csv \
|
||||
-l "$GPU_MEM_SAMPLE_INTERVAL_S" \
|
||||
> "$csv_path" 2>/dev/null &
|
||||
echo $!
|
||||
}
|
||||
|
||||
stop_gpu_monitor() {
|
||||
local pid="$1"
|
||||
if kill -0 "$pid" 2>/dev/null; then
|
||||
kill "$pid" 2>/dev/null || true
|
||||
sleep 1
|
||||
kill -9 "$pid" 2>/dev/null || true
|
||||
fi
|
||||
}
|
||||
|
||||
append_scenario_record() {
|
||||
local result_root="$1"
|
||||
local json_path="$result_root/results.json"
|
||||
shift
|
||||
local scenario_json
|
||||
scenario_json="$("$PYTHON" -c "
|
||||
import json, sys
|
||||
pairs = [a.split('=', 1) for a in sys.argv[1:]]
|
||||
d = {}
|
||||
for k, v in pairs:
|
||||
try:
|
||||
d[k] = json.loads(v)
|
||||
except json.JSONDecodeError:
|
||||
d[k] = v
|
||||
print(json.dumps(d, ensure_ascii=False))
|
||||
" "$@")"
|
||||
PYTHON="$PYTHON" append_scenario_to_json "$json_path" "$scenario_json"
|
||||
}
|
||||
|
||||
record_skipped_csv() {
|
||||
local csv_path="$1"
|
||||
shift
|
||||
# Args: key=value
|
||||
local row
|
||||
row="$("$PYTHON" -c "
|
||||
import csv, json, sys, io
|
||||
pairs = [a.split('=', 1) for a in sys.argv[1:]]
|
||||
d = {}
|
||||
for k, v in pairs:
|
||||
try:
|
||||
d[k] = json.loads(v)
|
||||
except json.JSONDecodeError:
|
||||
d[k] = v
|
||||
buf = io.StringIO()
|
||||
writer = csv.DictWriter(buf, fieldnames=['engine','tp','dp','mark','isl','dsl','concurrency','status','reason','detail_log'], extrasaction='ignore')
|
||||
writer.writerow(d)
|
||||
print(buf.getvalue().strip())
|
||||
" "$@")"
|
||||
echo "$row" >> "$csv_path"
|
||||
}
|
||||
|
||||
skip_remaining_scenarios() {
|
||||
local result_root="$1"
|
||||
local scenario_tsv="$2"
|
||||
local start_index="$3"
|
||||
local status="$4"
|
||||
local reason="$5"
|
||||
local tp="$6"
|
||||
local dp="$7"
|
||||
local skipped_csv="${RESULT_BASE}/${RUN_ID}/skipped_after_oom.csv"
|
||||
|
||||
local i=0
|
||||
tail -n +2 "$scenario_tsv" | while IFS=$'\t' read -r mark isl dsl conc num; do
|
||||
if (( i < start_index )); then
|
||||
i=$((i + 1))
|
||||
continue
|
||||
fi
|
||||
i=$((i + 1))
|
||||
local sname="c${conc}_i${isl}_o${dsl}"
|
||||
if scenario_already_processed "$result_root" "$sname"; then
|
||||
continue
|
||||
fi
|
||||
append_scenario_record "$result_root" \
|
||||
"name=${sname}" \
|
||||
"config=$(jq -n --arg phase main --argjson c "$conc" --argjson i "$isl" --argjson o "$dsl" --arg dataset random --argjson n "$num" '{phase: $phase, concurrency: $c, input_len: $i, output_len: $o, dataset: $dataset, num_prompts: $n}')" \
|
||||
"status=\"${status}\"" \
|
||||
"note=\"${reason}\""
|
||||
record_skipped_csv "$skipped_csv" \
|
||||
"engine=sglang" "tp=${tp}" "dp=${dp}" "mark=${mark}" "isl=${isl}" "dsl=${dsl}" "concurrency=${conc}" "status=${status}" "reason=${reason}"
|
||||
done
|
||||
}
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Per-configuration runner
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
run_parallel_config() {
|
||||
local tp="$1"
|
||||
local dp="$2"
|
||||
local config_label="tp${tp}_dp${dp}"
|
||||
local result_root="${RESULT_BASE}/${RUN_ID}/${config_label}"
|
||||
local raw_dir="${result_root}/raw_outputs"
|
||||
local gpu_log_dir="${result_root}/gpu_logs"
|
||||
local phase_log_dir="${result_root}/logs"
|
||||
mkdir -p "$raw_dir" "$gpu_log_dir" "$phase_log_dir"
|
||||
|
||||
log "===== ${config_label} START ====="
|
||||
|
||||
# Generate scenario list for this config.
|
||||
local scenario_tsv="${result_root}/scenarios.tsv"
|
||||
"$PYTHON" "${SCRIPT_DIR}/generate_scenarios.py" \
|
||||
--matrix "$MATRIX_FILE" \
|
||||
--mode "$MATRIX_MODE" \
|
||||
> "$scenario_tsv"
|
||||
local total_scenarios
|
||||
total_scenarios="$(tail -n +2 "$scenario_tsv" | wc -l)"
|
||||
log "generated ${total_scenarios} scenarios for ${config_label}"
|
||||
|
||||
# Write metadata.
|
||||
ensure_result_root "$result_root"
|
||||
write_metadata_json \
|
||||
"${result_root}/results.json" \
|
||||
"${EXPERIMENT_NAME}_${config_label}" \
|
||||
"$RUN_ID" \
|
||||
"$MODEL_PATH" \
|
||||
"sglang" \
|
||||
"sglang" \
|
||||
"$HARDWARE" \
|
||||
"$ACCELERATOR" \
|
||||
"$CHIP" \
|
||||
"experiments/${EXPERIMENT_NAME}/run_bench.sh" \
|
||||
"$DOCKER_IMAGE" \
|
||||
"H200 SGLang TP×DP matrix for DeepSeek-V4-Flash on RTX 6000D"
|
||||
|
||||
local server_args_str
|
||||
server_args_str="$(build_server_args "$tp" "$dp")"
|
||||
jq --arg tp "$tp" --arg dp "$dp" --arg cuda "$CUDA_VISIBLE_DEVICES" --arg args "$server_args_str" \
|
||||
'.config = {
|
||||
"tp": ($tp | tonumber),
|
||||
"dp": ($dp | tonumber),
|
||||
"cuda_visible_devices": $cuda,
|
||||
"backend": "sglang",
|
||||
"server_start_script": "experiments/'${EXPERIMENT_NAME}'/start_sglang_dp.sh",
|
||||
"server_args": $args
|
||||
}' "${result_root}/results.json" > "${result_root}/results.json.tmp" && \
|
||||
mv "${result_root}/results.json.tmp" "${result_root}/results.json"
|
||||
|
||||
if [[ "$DRY_RUN" == "1" ]]; then
|
||||
log "DRY_RUN: would start server with args: ${server_args_str}"
|
||||
local line
|
||||
tail -n +2 "$scenario_tsv" | while IFS=$'\t' read -r mark isl dsl conc num; do
|
||||
log "DRY_RUN: ${config_label} scenario mark=${mark} c=${conc} i=${isl} o=${dsl} n=${num}"
|
||||
done
|
||||
log "===== ${config_label} DONE (dry run) ====="
|
||||
return 0
|
||||
fi
|
||||
|
||||
# Initialize skipped_after_oom.csv for this run.
|
||||
local skipped_csv="${RESULT_BASE}/${RUN_ID}/skipped_after_oom.csv"
|
||||
if [[ ! -f "$skipped_csv" ]]; then
|
||||
echo "engine,tp,dp,mark,isl,dsl,concurrency,status,reason,detail_log" > "$skipped_csv"
|
||||
fi
|
||||
|
||||
# Start server once for this TP×DP config.
|
||||
if ! start_server "$tp" "$dp"; then
|
||||
log "ERROR: ${config_label} failed to start; skipping all scenarios"
|
||||
skip_remaining_scenarios "$result_root" "$scenario_tsv" 0 "SKIPPED_SERVICE_START_FAILED" "service failed to start" "$tp" "$dp"
|
||||
log "===== ${config_label} DONE ====="
|
||||
return 0
|
||||
fi
|
||||
|
||||
# Warmup with a small prompt before the first scenario.
|
||||
run_warmup 1024 128 || true
|
||||
|
||||
# Read scenarios into an array so we can skip remaining entries on failure.
|
||||
local -a scenarios=()
|
||||
while IFS= read -r line; do
|
||||
scenarios+=("$line")
|
||||
done < <(tail -n +2 "$scenario_tsv")
|
||||
|
||||
local i mark isl dsl conc num
|
||||
local output_file detail_log gpu_csv sname bench_rc
|
||||
for (( i = 0; i < ${#scenarios[@]}; i++ )); do
|
||||
IFS=$'\t' read -r mark isl dsl conc num <<< "${scenarios[$i]}"
|
||||
|
||||
if [[ "$GRID_LIMIT" -gt 0 && "$i" -ge "$GRID_LIMIT" ]]; then
|
||||
log "GRID_LIMIT=${GRID_LIMIT} reached; skipping remaining scenarios"
|
||||
skip_remaining_scenarios "$result_root" "$scenario_tsv" "$i" "SKIPPED_GRID_LIMIT" "GRID_LIMIT reached" "$tp" "$dp"
|
||||
break
|
||||
fi
|
||||
|
||||
sname="c${conc}_i${isl}_o${dsl}"
|
||||
output_file="${raw_dir}/sglang_main_${conc}_${isl}_${dsl}.jsonl"
|
||||
detail_log="${phase_log_dir}/sglang_${config_label}_${sname}.log"
|
||||
gpu_csv="${gpu_log_dir}/gpu_mem_${conc}_${isl}_${dsl}.csv"
|
||||
|
||||
if scenario_already_completed "$output_file" "$num" || scenario_already_processed "$result_root" "$sname"; then
|
||||
log "skipping already-processed ${config_label} scenario: ${sname}"
|
||||
continue
|
||||
fi
|
||||
|
||||
log "running ${config_label} scenario: mark=${mark} c=${conc} i=${isl} o=${dsl} n=${num}"
|
||||
|
||||
local gpu_pid
|
||||
gpu_pid="$(start_gpu_monitor "$gpu_csv")"
|
||||
|
||||
bench_rc=0
|
||||
timeout "$SCENARIO_TIMEOUT_S" bash -c '
|
||||
run_bench_serving \
|
||||
--backend sglang \
|
||||
--host 127.0.0.1 \
|
||||
--port "'"$SGLANG_PORT"'" \
|
||||
--dataset-name random \
|
||||
--dataset-path "'"$DATASET_PATH"'" \
|
||||
--random-input-len "'"$isl"'" \
|
||||
--random-output-len "'"$dsl"'" \
|
||||
--num-prompts "'"$num"'" \
|
||||
--max-concurrency "'"$conc"'" \
|
||||
--request-rate 10000 \
|
||||
--output-file "'"$output_file"'" \
|
||||
--output-details \
|
||||
> "'"$detail_log"'" 2>&1
|
||||
' || bench_rc=$?
|
||||
|
||||
stop_gpu_monitor "$gpu_pid"
|
||||
|
||||
if [[ "$bench_rc" -eq 0 ]]; then
|
||||
log "finished ${config_label} scenario: output=${output_file}"
|
||||
append_scenario_record "$result_root" \
|
||||
"name=${sname}" \
|
||||
"config=$(jq -n --arg phase main --argjson c "$conc" --argjson i "$isl" --argjson o "$dsl" --arg dataset random --argjson n "$num" '{phase: $phase, concurrency: $c, input_len: $i, output_len: $o, dataset: $dataset, num_prompts: $n}')" \
|
||||
"status=\"completed\"" \
|
||||
"note=\"benchmark finished successfully\""
|
||||
continue
|
||||
fi
|
||||
|
||||
# Failure handling.
|
||||
if detect_oom "$detail_log" "${log_dir_global}/sglang_tp${tp}_dp${dp}.server.outer.log"; then
|
||||
log "ERROR: ${config_label} scenario ${sname} triggered OOM; stopping config"
|
||||
append_scenario_record "$result_root" \
|
||||
"name=${sname}" \
|
||||
"config=$(jq -n --arg phase main --argjson c "$conc" --argjson i "$isl" --argjson o "$dsl" --arg dataset random --argjson n "$num" '{phase: $phase, concurrency: $c, input_len: $i, output_len: $o, dataset: $dataset, num_prompts: $n}')" \
|
||||
"status=\"OOM\"" \
|
||||
"note=\"detected CUDA out-of-memory\""
|
||||
record_skipped_csv "$skipped_csv" \
|
||||
"engine=sglang" "tp=${tp}" "dp=${dp}" "mark=${mark}" "isl=${isl}" "dsl=${dsl}" "concurrency=${conc}" "status=OOM" "reason=detected CUDA out-of-memory" "detail_log=${detail_log}"
|
||||
stop_server "$tp" "$dp"
|
||||
skip_remaining_scenarios "$result_root" "$scenario_tsv" "$((i + 1))" "SKIPPED_AFTER_OOM" "previous case OOM" "$tp" "$dp"
|
||||
break
|
||||
fi
|
||||
|
||||
log "ERROR: ${config_label} scenario ${sname} failed (rc=${bench_rc}); see ${detail_log}"
|
||||
if [[ "$mark" == "P" ]]; then
|
||||
log "optional (P) scenario failed; recording as skipped and continuing"
|
||||
append_scenario_record "$result_root" \
|
||||
"name=${sname}" \
|
||||
"config=$(jq -n --arg phase main --argjson c "$conc" --argjson i "$isl" --argjson o "$dsl" --arg dataset random --argjson n "$num" '{phase: $phase, concurrency: $c, input_len: $i, output_len: $o, dataset: $dataset, num_prompts: $n}')" \
|
||||
"status=\"skipped_optional\"" \
|
||||
"note=\"optional scenario failed (rc=${bench_rc})\""
|
||||
record_skipped_csv "$skipped_csv" \
|
||||
"engine=sglang" "tp=${tp}" "dp=${dp}" "mark=${mark}" "isl=${isl}" "dsl=${dsl}" "concurrency=${conc}" "status=skipped_optional" "reason=optional scenario failed (rc=${bench_rc})" "detail_log=${detail_log}"
|
||||
continue
|
||||
fi
|
||||
|
||||
# Mandatory scenario failed but not OOM: try to restart the server.
|
||||
if restart_server "$tp" "$dp"; then
|
||||
run_warmup 1024 128 || true
|
||||
log "resuming ${config_label} after server restart"
|
||||
continue
|
||||
fi
|
||||
|
||||
log "ERROR: ${config_label} server restart failed; skipping remaining scenarios"
|
||||
append_scenario_record "$result_root" \
|
||||
"name=${sname}" \
|
||||
"config=$(jq -n --arg phase main --argjson c "$conc" --argjson i "$isl" --argjson o "$dsl" --arg dataset random --argjson n "$num" '{phase: $phase, concurrency: $c, input_len: $i, output_len: $o, dataset: $dataset, num_prompts: $n}')" \
|
||||
"status=\"FAILED\"" \
|
||||
"note=\"scenario failed and server restart failed (rc=${bench_rc})\""
|
||||
record_skipped_csv "$skipped_csv" \
|
||||
"engine=sglang" "tp=${tp}" "dp=${dp}" "mark=${mark}" "isl=${isl}" "dsl=${dsl}" "concurrency=${conc}" "status=FAILED" "reason=scenario failed and server restart failed" "detail_log=${detail_log}"
|
||||
skip_remaining_scenarios "$result_root" "$scenario_tsv" "$((i + 1))" "SKIPPED_RESTART_FAILED" "server restart failed" "$tp" "$dp"
|
||||
break
|
||||
done
|
||||
|
||||
stop_server "$tp" "$dp"
|
||||
|
||||
# Parse results.
|
||||
log "parsing ${config_label} results"
|
||||
"$PYTHON" "${SCRIPT_DIR}/../../scripts/common/parse_backend.py" "$result_root" --backend sglang \
|
||||
>> "${phase_log_dir}/parse.log" 2>&1 || {
|
||||
log "WARNING: parser failed for ${config_label}; see ${phase_log_dir}/parse.log"
|
||||
}
|
||||
|
||||
log "===== ${config_label} DONE ====="
|
||||
}
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Main
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Cleanup any leftovers.
|
||||
for cfg in "${PARALLEL_CONFIGS[@]}"; do
|
||||
read -r tp dp <<< "$cfg"
|
||||
stop_server "$tp" "$dp"
|
||||
done
|
||||
|
||||
# Run each parallel configuration.
|
||||
for cfg in "${PARALLEL_CONFIGS[@]}"; do
|
||||
read -r tp dp <<< "$cfg"
|
||||
run_parallel_config "$tp" "$dp"
|
||||
done
|
||||
|
||||
# Generate cross-configuration comparison.
|
||||
log "generating comparison report"
|
||||
"$PYTHON" "${SCRIPT_DIR}/compare.py" \
|
||||
--run-root "${RESULT_BASE}/${RUN_ID}" \
|
||||
--output "${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}"
|
||||
Loading…
x
Reference in New Issue
Block a user