74194e660a
Add v4 sweep results and post-mortem analysis showing:
- direct-to-D path: 54.3% (1P7D) / 58.0% (2P6D) of requests now use
KVC cleanly. P50=0.5s and TTFT P50=0.043s; this path beats baseline
8DP across the board (P50 -24%, TTFT P50 -54%, TTFT P90 -79%).
- Overall vs baseline (errors+truncated excluded):
v4 2P6D P50=0.85s vs baseline 0.66s (28% slower).
Reason is not errors -- 35% of requests still hit
fallback-large-append-session-cap, where capacity-based
cap = usable_tokens / target_tokens evaluates to 1-2 (not 16)
for large agentic inputs.
- 9-10% errors on KVC variants are mooncake TCP transfer timeouts,
not SGLang logic bugs. Prefill log shows
"Failed to send kv chunk ... 32s timeout ... session not alive".
Errors concentrate in turn>=31 (large inputs) after run >44.8%.
Track:
- docs/KVC_DEBUG_JOURNEY_V1_TO_V4.md: append v4 results table,
per-mode breakdown, and error root cause.
- scripts/analysis/{analyze_v3,analyze_v4,analyze_errors,compare_no_error}.py
- outputs/qwen3-30b-tp1-v{3,4}*/exp*_summary.json (force-added,
small JSON; metrics.jsonl excluded due to size).
- outputs/qwen3-30b-tp1-v{3,4}*/sweep_results.txt
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
53 lines
2.0 KiB
Python
53 lines
2.0 KiB
Python
#!/usr/bin/env python3
|
|
"""V4 results analysis: errors, execution modes, latency by mode."""
|
|
import json
|
|
import numpy as np
|
|
from pathlib import Path
|
|
from collections import Counter
|
|
|
|
BASE = Path(__file__).parent
|
|
|
|
def load_rows(jsonl_path):
|
|
rows = []
|
|
with open(jsonl_path) as f:
|
|
for line in f:
|
|
rows.append(json.loads(line))
|
|
return rows
|
|
|
|
for name, path in [
|
|
("Exp1 1P7D cap=16", BASE / "exp1_1p7d_kvc_cap16_metrics.jsonl"),
|
|
("Exp2 2P6D cap=16", BASE / "exp2_2p6d_kvc_cap16_metrics.jsonl"),
|
|
]:
|
|
rows = load_rows(path)
|
|
print(f"\n========== {name} ==========")
|
|
ok = [r for r in rows if r.get("error") is None]
|
|
err = [r for r in rows if r.get("error") is not None]
|
|
print(f"Total: {len(rows)}, OK: {len(ok)}, Errors: {len(err)}")
|
|
|
|
# Errors finish_reason
|
|
if err:
|
|
finish_reasons = Counter()
|
|
for r in err:
|
|
fr = str(r.get("finish_reason") or r.get("error") or "?")
|
|
# Truncate long messages
|
|
short = fr[:120]
|
|
finish_reasons[short] += 1
|
|
print(f"\nError finish_reasons (top 5):")
|
|
for fr, cnt in finish_reasons.most_common(5):
|
|
print(f" {cnt}x: {fr}")
|
|
|
|
# Execution mode latency breakdown
|
|
modes = Counter(r["execution_mode"] for r in ok)
|
|
print(f"\nTop execution modes by latency:")
|
|
print(f"{'mode':<55}{'n':<8}{'%':<8}{'P50 lat':<10}{'P90 lat':<10}{'TTFT P50':<10}")
|
|
for mode, count in modes.most_common(8):
|
|
mode_rows = [r for r in ok if r["execution_mode"] == mode]
|
|
lats = [r["latency_s"] for r in mode_rows]
|
|
ttfts = [r["ttft_s"] for r in mode_rows]
|
|
print(f" {mode:<53}{count:<8}{count/len(ok)*100:>5.1f}% {np.percentile(lats,50):>7.3f}s {np.percentile(lats,90):>7.3f}s {np.percentile(ttfts,50):>7.3f}s")
|
|
|
|
# Per-D load
|
|
per_d = Counter(r.get("assigned_decode_node", "?") for r in ok)
|
|
print(f"\nPer-D load: max/min ratio = {max(per_d.values())/max(min(per_d.values()),1):.2f}x")
|
|
print(f" {dict(per_d.most_common())}")
|