Gahow Wang
a4a171d425
runner/servers gain --tp (xserv --tp N; llama.cpp --split-mode row) and --llama-devices so llama can run on a disjoint GPU group. run_tp_parallel.sh runs xserv (GPU 0..N-1) and llama.cpp (GPU 4..4+N-1) concurrently per TP, matching the box's 0-3 / 4-7 PHB groups. summarize_tp.py tabulates the sweep. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
25 lines
1.0 KiB
Python
25 lines
1.0 KiB
Python
"""Summarize the concurrent TP sweep: bench-out/tp{1,2,4}-{xserv,llama}."""
|
|
import glob
|
|
import json
|
|
import os
|
|
import sys
|
|
|
|
base = sys.argv[1] if len(sys.argv) > 1 else "bench-out"
|
|
rows = []
|
|
for tp in (1, 2, 4):
|
|
for sysname in ("xserv", "llama"):
|
|
files = sorted(glob.glob(os.path.join(base, f"tp{tp}-{sysname}", "comparison-*.json")))
|
|
if not files:
|
|
continue
|
|
d = json.load(open(files[-1]))
|
|
for r in d["quality"]["summary"]:
|
|
rows.append((tp, sysname, r["task"], r["n_correct"], r["n_total"],
|
|
r["accuracy"] * 100, r["mean_completion_tokens"],
|
|
r["mean_ttft_ms"], r["mean_tpot_ms"], r["wall_s"]))
|
|
|
|
print("%-3s %-7s %-9s %-9s %7s %9s %9s %10s %9s" %
|
|
("TP", "engine", "task", "correct", "acc%", "mean_tok", "TTFT_ms", "TPOT_ms", "wall_s"))
|
|
for (tp, s, task, nc, nt, acc, tok, ttft, tpot, wall) in rows:
|
|
print("%-3d %-7s %-9s %-9s %6.1f%% %9.0f %9.1f %10.2f %9.0f" %
|
|
(tp, s, task, f"{nc}/{nt}", acc, tok, ttft, tpot, wall))
|