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/
89 lines
3.0 KiB
Python
89 lines
3.0 KiB
Python
"""
|
|
Gemma 4 26B-A4B Q4_K_M - 76.4 t/s 재현 테스트
|
|
이전 최적값: ngl=999 t=6 ub=512 b=2048 ctk=f16 ctv=f16
|
|
"""
|
|
import subprocess, time, json, urllib.request, sys, os
|
|
|
|
try: sys.stdout.reconfigure(encoding='utf-8')
|
|
except: pass
|
|
|
|
LLAMA = os.path.join(os.getcwd(), "llama_bin_run", "llama-server.exe")
|
|
MODEL = os.path.join(os.getcwd(), "models", "gemma-4-26B-A4B-it-Q4_K_M.gguf")
|
|
|
|
subprocess.run(["taskkill", "/F", "/IM", "llama-server.exe"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
|
|
time.sleep(3)
|
|
|
|
cmd = [
|
|
LLAMA, "--model", MODEL,
|
|
"-ngl", "999", "-c", "262144", "-np", "1", "-fa", "on",
|
|
"--cache-type-k", "f16", "--cache-type-v", "f16",
|
|
"-ub", "512", "-b", "2048", "-t", "6", "-tb", "6",
|
|
"--prio", "3", "--mlock", "--poll", "50",
|
|
"--port", "8000", "--host", "0.0.0.0",
|
|
]
|
|
|
|
print("[1/4] Starting Gemma4 26B Q4_K_M (76.4 t/s config)...")
|
|
server = subprocess.Popen(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
|
|
|
|
print("[2/4] Waiting for boot...")
|
|
healthy = False
|
|
for sec in range(180):
|
|
time.sleep(1)
|
|
if server.poll() is not None:
|
|
print(f" !! CRASHED (exit code {server.returncode})")
|
|
sys.exit(1)
|
|
try:
|
|
with urllib.request.urlopen("http://127.0.0.1:8000/health", timeout=1) as r:
|
|
if json.loads(r.read()).get("status") == "ok":
|
|
healthy = True; break
|
|
except: pass
|
|
if sec % 10 == 9: print(f" ... {sec+1}s")
|
|
|
|
if not healthy:
|
|
print(" FAIL: boot timeout"); server.kill(); sys.exit(1)
|
|
|
|
print(f" OK!")
|
|
try:
|
|
v = subprocess.run(["nvidia-smi", "--query-gpu=index,memory.used,memory.total", "--format=csv,noheader,nounits"], capture_output=True, text=True, timeout=5)
|
|
print(f" VRAM: {v.stdout.strip()}")
|
|
except: pass
|
|
|
|
def bench(n):
|
|
payload = json.dumps({"messages": [{"role": "user", "content": "Count from 1 to 50, each number on a new line."}], "max_tokens": n, "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=120) as r:
|
|
res = json.loads(r.read())
|
|
el = time.time() - t0
|
|
ct = res["usage"]["completion_tokens"]
|
|
return ct / el, ct, el
|
|
|
|
try: bench(10)
|
|
except: pass
|
|
|
|
print("[3/4] Running 5x benchmark (200 tokens)...")
|
|
results = []
|
|
for i in range(5):
|
|
tps, tok, el = bench(200)
|
|
results.append(tps)
|
|
print(f" Run {i+1}: {tps:.2f} t/s ({tok} tok / {el:.2f}s)")
|
|
|
|
avg = sum(results) / len(results)
|
|
best = max(results)
|
|
worst = min(results)
|
|
summary = f"""
|
|
==================================================
|
|
Gemma4 26B Q4_K_M 5-Run Results:
|
|
AVG: {avg:.2f} t/s
|
|
BEST: {best:.2f} t/s
|
|
MIN: {worst:.2f} t/s
|
|
Runs: {[f'{r:.2f}' for r in results]}
|
|
==================================================
|
|
"""
|
|
print(summary)
|
|
with open("scripts/gemma4_test_result.txt", "w") as f:
|
|
f.write(summary)
|
|
|
|
server.kill()
|
|
subprocess.run(["taskkill", "/F", "/IM", "llama-server.exe"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
|