c111b3a9b0
Phase 01 (LLM Tuning): - Gemma4 26B: 74.65 t/s (fast) - Qwen 35B: 61.62 t/s (balanced) - Gemma4 31B: 16.0 t/s (deep-coder) - Qwen 27B: 16.7 t/s (deep-logic) - Qwen 122B: 8.95 t/s (ultra, GPU 1 only) Phase 02 (API Engine): - FastAPI reverse proxy on port 8000 - /engine/switch hot-swap with 503 protection - config/engine_models.json as single source of truth - Replaced 4 individual .bat files with unified engine File cleanup: - scripts/ 85 files -> 9 + _archive/ - Root .bat files -> _archive/
68 lines
2.0 KiB
Python
68 lines
2.0 KiB
Python
import subprocess
|
|
import time
|
|
import json
|
|
import urllib.request
|
|
import sys
|
|
import os
|
|
|
|
try: sys.stdout.reconfigure(encoding='utf-8')
|
|
except AttributeError: pass
|
|
|
|
MODEL = r"models\Qwen3.5-35B-A3B-Q4_K_M.gguf"
|
|
LLAMA_SERVER = r"llama_bin_run\llama-server.exe"
|
|
|
|
subprocess.run(["taskkill", "/F", "/IM", "llama-server.exe"], capture_output=True)
|
|
time.sleep(2)
|
|
|
|
cmd = [
|
|
LLAMA_SERVER, "--model", MODEL,
|
|
"-ngl", "999", "-c", "262144", "-np", "1", "-fa", "on",
|
|
"--cache-type-k", "q4_0", "--cache-type-v", "q4_0",
|
|
"-ub", "128", "-b", "512", "-t", "6", "-tb", "6",
|
|
"--prio", "3", "--port", "8000", "--host", "0.0.0.0",
|
|
"-ts", "0.44,0.56"
|
|
]
|
|
|
|
print(f"🚀 Starting Challenge (0.44, 0.56) ...")
|
|
proc = subprocess.Popen(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
|
|
|
|
ready = False
|
|
for i in range(120):
|
|
try:
|
|
req = urllib.request.Request("http://127.0.0.1:8000/health")
|
|
with urllib.request.urlopen(req, timeout=1) as r:
|
|
if json.loads(r.read()).get("status") == "ok":
|
|
ready = True
|
|
break
|
|
except:
|
|
pass
|
|
print(f" booting... {i}s", end='\r', flush=True)
|
|
time.sleep(1)
|
|
|
|
if not ready:
|
|
print("\n❌ FAILED to boot.")
|
|
proc.kill()
|
|
sys.exit(1)
|
|
|
|
print("\n✅ Booted! Testing 200 tokens...")
|
|
try:
|
|
payload = json.dumps({
|
|
"messages": [{"role": "user", "content": "Count from 1 to 50, each number on a new line."}],
|
|
"max_tokens": 200, "temperature": 0
|
|
}).encode()
|
|
req = urllib.request.Request("http://127.0.0.1:8000/v1/chat/completions", data=payload, headers={"Content-Type": "application/json"})
|
|
t0 = time.time()
|
|
with urllib.request.urlopen(req, timeout=300) as r:
|
|
res = json.loads(r.read())
|
|
el = time.time() - t0
|
|
ct = res["usage"]["completion_tokens"]
|
|
tps = ct / el
|
|
print("="*50)
|
|
print(f"★ 0.44 / 0.56 RESULT: {tps:.2f} t/s ★")
|
|
print(f" Tokens: {ct} | Time: {el:.2f}s")
|
|
print("="*50)
|
|
except Exception as e:
|
|
print(f"\n❌ Benchmark Error: {e}")
|
|
|
|
proc.kill()
|