feat(experiments): E1 sweep on 50-session deterministic subset

scripts/sample_trace_subset.py — file-order head-cut that takes the
first N sessions of a converted trace. No RNG, no hashing — same
input yields byte-identical output (the included assertion compares
md5 across two runs).

scripts/sweep_e1_naive_1p3d.sh — E1 of ONBOARDING_NEXT_AGENT_ZH §3.1:
mechanism=pd-disaggregation, policy=kv-aware, 1P3D, RDMA on
(mlx5_60). Defaults to outputs/inferact_50sess.jsonl so E1 and E2
can share the exact same subset; override via TRACE= env var to run
on the full 20,230-request trace.

Reproducing the subset:
  uv run --no-sync python scripts/sample_trace_subset.py \\
    --input outputs/inferact_codex_swebenchpro.jsonl \\
    --output outputs/inferact_50sess.jsonl \\
    --sessions 50
  # expected output_md5: 7bb263a32600ef5a6ef5099ba340a487
  # 1285 requests, mean input_length 67631 tokens

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
tim
2026-05-12 00:21:36 +08:00
parent b55371fe69
commit bb9cc249cd
2 changed files with 163 additions and 0 deletions

View File

@@ -0,0 +1,81 @@
"""Deterministically slice the first N sessions of an agentic-pd-hybrid trace.
Method: scan in file order, count records whose `parent_chat_id == -1` (= a
session's turn 0), and write every record until the (N+1)-th such record is
seen. No RNG, no hashing — re-running on the same input produces a byte-
identical output. Used to derive matched subsets for paired sweeps (E1 vs E2)
without spending GPU hours on the full trace.
Usage:
uv run --no-sync python scripts/sample_trace_subset.py \
--input outputs/inferact_codex_swebenchpro.jsonl \
--output outputs/inferact_50sess.jsonl \
--sessions 50
"""
from __future__ import annotations
import argparse
import hashlib
import json
import sys
from pathlib import Path
def slice_first_n_sessions(input_path: Path, output_path: Path, n_sessions: int) -> dict:
sessions_seen = 0
requests_written = 0
input_length_sum = 0
output_length_sum = 0
min_in = float("inf")
max_in = 0
with input_path.open("r", encoding="utf-8") as f_in, output_path.open(
"w", encoding="utf-8"
) as f_out:
for line in f_in:
rec = json.loads(line)
if rec["parent_chat_id"] == -1:
sessions_seen += 1
if sessions_seen > n_sessions:
break
f_out.write(line)
requests_written += 1
il = int(rec["input_length"])
input_length_sum += il
output_length_sum += int(rec["output_length"])
if il < min_in:
min_in = il
if il > max_in:
max_in = il
h = hashlib.md5(output_path.read_bytes()).hexdigest()
return {
"sessions": min(sessions_seen, n_sessions),
"requests": requests_written,
"input_length_mean": input_length_sum / max(1, requests_written),
"input_length_min": int(min_in) if min_in != float("inf") else 0,
"input_length_max": max_in,
"output_length_mean": output_length_sum / max(1, requests_written),
"output_md5": h,
}
def main() -> None:
p = argparse.ArgumentParser(description=__doc__)
p.add_argument(
"--input",
type=Path,
default=Path("outputs/inferact_codex_swebenchpro.jsonl"),
)
p.add_argument("--output", type=Path, required=True)
p.add_argument("--sessions", type=int, default=50)
args = p.parse_args()
args.output.parent.mkdir(parents=True, exist_ok=True)
stats = slice_first_n_sessions(args.input, args.output, args.sessions)
print(json.dumps(stats, indent=2), file=sys.stderr)
if __name__ == "__main__":
main()

82
scripts/sweep_e1_naive_1p3d.sh Executable file
View File

@@ -0,0 +1,82 @@
#!/usr/bin/env bash
# E1 — naive 1P3D + kv-aware + RDMA, ts=1
#
# Tests hypothesis H1 from ONBOARDING_NEXT_AGENT_ZH §3.1: separate the
# contribution of "1P3D topology + kv-aware policy" from "KVC layer
# (admission / migration / direct-to-D)".
#
# Mechanism = pd-disaggregation (no KVC layer); policy = kv-aware.
# Topology = 1P3D, RDMA on (mlx5_60 = cuda:0 NUMA-local).
#
# Prerequisites:
# - source scripts/setup_env.sh (sets CUDA_HOME etc.)
# - outputs/inferact_codex_swebenchpro.jsonl exists
# (run scripts/convert_inferact_to_trace.py if not)
#
# Usage:
# bash scripts/sweep_e1_naive_1p3d.sh
#
# Override defaults via env:
# MODEL=/path TRACE=path OUTPUT=path IB_DEVICE=mlx5_XX bash scripts/sweep_e1_naive_1p3d.sh
set -euo pipefail
cd "$(dirname "$0")/.."
if [ -z "${CUDA_HOME:-}" ]; then
echo "ERROR: CUDA_HOME not set. Source scripts/setup_env.sh first." >&2
exit 1
fi
MODEL=${MODEL:-/mnt/models/Qwen/Qwen3-30B-A3B-Instruct-2507}
TRACE=${TRACE:-outputs/inferact_50sess.jsonl}
OUTPUT=${OUTPUT:-outputs/e1_naive_1p3d_kvaware_rdma_50sess}
IB_DEVICE=${IB_DEVICE:-mlx5_60}
if [ ! -f "$TRACE" ]; then
echo "ERROR: trace not found at $TRACE" >&2
echo "Run: uv run --no-sync python scripts/convert_inferact_to_trace.py --output $TRACE" >&2
exit 1
fi
mkdir -p "$OUTPUT"
LOG="$OUTPUT/sweep.log"
log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" | tee -a "$LOG"; }
log "=== E1: naive 1P3D kv-aware + RDMA, ts=1 ==="
log "MODEL=$MODEL"
log "TRACE=$TRACE ($(wc -l < $TRACE) requests)"
log "OUTPUT=$OUTPUT"
log "IB_DEVICE=$IB_DEVICE"
label=e1_naive_1p3d_kvaware_run1
log ""
log "=== [E1] $label starting ==="
uv run --no-sync python -m agentic_pd_hybrid.cli benchmark-live \
--trace "$TRACE" \
--output-root "$OUTPUT" \
--mechanism pd-disaggregation \
--policy kv-aware \
--model-path "$MODEL" \
--prefill-workers 1 --decode-workers 3 \
--prefill-tp-size 1 --decode-tp-size 1 \
--prefill-gpu-ids 0 --decode-gpu-ids 1,2,3 \
--transfer-backend mooncake \
--force-rdma --ib-device "$IB_DEVICE" \
--gpu-budget 4 \
--time-scale 1 \
--session-sample-rate 1.0 \
--target-duration-s 100000 \
--concurrency-limit 32 \
--timeout-s 1800 \
--request-timeout-s 300 2>&1 | tee -a "$LOG"
run_dir=$(ls -td "$OUTPUT"/pd-disaggregation-*/ 2>/dev/null | head -1)
log "=== [E1] $label COMPLETED, artifacts at $run_dir ==="
if [ -f "$run_dir/request-metrics.jsonl.summary.json" ]; then
cp "$run_dir/request-metrics.jsonl.summary.json" "$OUTPUT/${label}_summary.json"
cp "$run_dir/request-metrics.jsonl" "$OUTPUT/${label}_metrics.jsonl"
log "=== summary saved to $OUTPUT/${label}_summary.json ==="
fi