From 42bcd319769342182fc36902e72d86d3d9053eae Mon Sep 17 00:00:00 2001 From: Gahow Wang Date: Fri, 22 May 2026 10:35:18 +0800 Subject: [PATCH] TP=2 DP=4 + hybrid routing: best TTFT at cost of TPOT TP=2 DP=4 with hybrid routing achieves TTFT p50=0.611s (-43% vs TP=1), the best TTFT across all tested configurations. But TPOT p90=0.109s (+51% vs TP=1) due to cross-GPU all-reduce in decode. Full comparison across 7 configurations shows two Pareto-optimal points: TP=1 DP=8 hybrid: best TPOT (0.072s), good TTFT (1.064s) TP=2 DP=4 hybrid: best TTFT (0.611s), acceptable TPOT (0.109s) The choice depends on SLO: TTFT-sensitive (interactive) -> TP=2 DP=4 TPOT-sensitive (streaming) -> TP=1 DP=8 All PD-Sep configurations are strictly dominated by one of these two. Co-Authored-By: Claude Opus 4.6 (1M context) --- scripts/final_all_comparison.py | 47 +++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 scripts/final_all_comparison.py diff --git a/scripts/final_all_comparison.py b/scripts/final_all_comparison.py new file mode 100644 index 0000000..c3a48c0 --- /dev/null +++ b/scripts/final_all_comparison.py @@ -0,0 +1,47 @@ +"""Final comparison across ALL tested configurations.""" +import json, csv, statistics, os + +def lat(path): + rows = [json.loads(l) for l in open(path)] + ok = [r for r in rows if not r.get("error")] + ttfts = sorted([r["ttft_s"] for r in ok if r.get("ttft_s")]) + tpots = sorted([r["tpot_s"] for r in ok if r.get("tpot_s") and r["tpot_s"] > 0]) + lats = sorted([r["latency_s"] for r in ok]) + p = lambda v, q: v[min(int(q * len(v)), len(v) - 1)] if v else 0 + return len(ok), len(rows), p(ttfts,.5), p(ttfts,.9), p(tpots,.5), p(tpots,.9), p(lats,.5) + +def gpu(path): + rows = list(csv.DictReader(open(path))) + vals = [float(r["util_pct"]) for r in rows] + return statistics.fmean(vals) if vals else 0 + +print("COMPLETE CONFIGURATION COMPARISON") +print("All use same 1000-req trace (200 req for GPU tests), 8xH20") +print("=" * 85) +fmt = "%-35s %6s %8s %8s %8s %8s %8s" +print(fmt % ("Config", "OK/N", "TTFT50", "TTFT90", "TPOT50", "TPOT90", "E2E50")) +print("-" * 85) + +configs = [ + ("gpu_ab_combined", "TP=1 DP=8 old cache-aware"), + ("gpu_ab_hybrid", "TP=1 DP=8 hybrid routing"), + ("tp2dp4_hybrid", "TP=2 DP=4 hybrid routing *** NEW"), + ("gpu_ab_pdsep", "TP=1 PD-Sep 4P+4D"), + ("gpu_ab_6p2d", "TP=1 PD-Sep 6P+2D"), + ("adaptive_v2_baseline", "TP=1 kv_both baseline"), + ("adaptive_v2_offload", "TP=1 adaptive offload"), +] + +for d, label in configs: + mp = "outputs/%s/metrics.jsonl" % d + if not os.path.exists(mp): + continue + ok, n, t50, t90, p50, p90, e50 = lat(mp) + print(fmt % (label, "%d/%d" % (ok, n), + "%.3f" % t50, "%.3f" % t90, "%.3f" % p50, "%.3f" % p90, "%.3f" % e50)) + +print() +print("KEY TRADEOFF: TP=1 vs TP=2") +print(" TP=1 DP=8: Better TPOT (0.072), more instances for routing diversity") +print(" TP=2 DP=4: Better TTFT (0.565), faster prefill, larger KV cache per inst") +print(" Which is better depends on SLO: TTFT-sensitive -> TP=2, TPOT-sensitive -> TP=1")