Compare commits
1 Commits
queue/288-
...
burn/model
| Author | SHA1 | Date | |
|---|---|---|---|
|
f8f4678ee4 |
284
scripts/benchmark_local_models.py
Normal file
284
scripts/benchmark_local_models.py
Normal file
@@ -0,0 +1,284 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Benchmark local Ollama models against the 50 tok/s UX threshold.
|
||||
|
||||
Usage:
|
||||
python3 scripts/benchmark_local_models.py [--models MODEL1,MODEL2] [--prompt PROMPT] [--rounds N]
|
||||
python3 scripts/benchmark_local_models.py --all # test all pulled models
|
||||
python3 scripts/benchmark_local_models.py --json # JSON output for CI
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
import urllib.request
|
||||
import urllib.error
|
||||
from dataclasses import dataclass, asdict
|
||||
from typing import Optional
|
||||
|
||||
OLLAMA_BASE = os.environ.get("OLLAMA_BASE_URL", "http://localhost:11434")
|
||||
THRESHOLD_TOK_S = 50.0
|
||||
|
||||
BENCHMARK_PROMPT = (
|
||||
"Explain the difference between TCP and UDP protocols. "
|
||||
"Cover reliability, ordering, speed, and use cases. "
|
||||
"Be thorough but concise. Write at least 300 words."
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class BenchmarkResult:
|
||||
model: str
|
||||
size_gb: float
|
||||
prompt_tokens: int
|
||||
eval_tokens: int
|
||||
eval_duration_s: float
|
||||
tokens_per_second: float
|
||||
total_duration_s: float
|
||||
rounds: int
|
||||
avg_tok_s: float
|
||||
meets_threshold: bool
|
||||
error: Optional[str] = None
|
||||
|
||||
|
||||
def get_models() -> list[dict]:
|
||||
"""List all pulled Ollama models."""
|
||||
url = f"{OLLAMA_BASE}/api/tags"
|
||||
try:
|
||||
req = urllib.request.Request(url)
|
||||
with urllib.request.urlopen(req, timeout=10) as resp:
|
||||
data = json.loads(resp.read())
|
||||
return data.get("models", [])
|
||||
except Exception as e:
|
||||
print(f"Error connecting to Ollama at {OLLAMA_BASE}: {e}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
def benchmark_model(model: str, prompt: str, num_predict: int = 512) -> dict:
|
||||
"""Run a single benchmark generation, return timing stats."""
|
||||
url = f"{OLLAMA_BASE}/api/generate"
|
||||
payload = json.dumps({
|
||||
"model": model,
|
||||
"prompt": prompt,
|
||||
"stream": False,
|
||||
"options": {
|
||||
"num_predict": num_predict,
|
||||
"temperature": 0.1, # low temp for consistent output
|
||||
},
|
||||
}).encode()
|
||||
|
||||
req = urllib.request.Request(url, data=payload, method="POST")
|
||||
req.add_header("Content-Type", "application/json")
|
||||
|
||||
start = time.monotonic()
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=300) as resp:
|
||||
data = json.loads(resp.read())
|
||||
except urllib.error.HTTPError as e:
|
||||
body = e.read().decode() if e.fp else str(e)
|
||||
raise RuntimeError(f"HTTP {e.code}: {body[:200]}")
|
||||
except Exception as e:
|
||||
raise RuntimeError(str(e))
|
||||
elapsed = time.monotonic() - start
|
||||
|
||||
prompt_tokens = data.get("prompt_eval_count", 0)
|
||||
eval_tokens = data.get("eval_count", 0)
|
||||
eval_duration_ns = data.get("eval_duration", 0)
|
||||
total_duration_ns = data.get("total_duration", 0)
|
||||
|
||||
eval_duration_s = eval_duration_ns / 1e9 if eval_duration_ns else elapsed
|
||||
total_duration_s = total_duration_ns / 1e9 if total_duration_ns else elapsed
|
||||
tok_s = eval_tokens / eval_duration_s if eval_duration_s > 0 else 0.0
|
||||
|
||||
return {
|
||||
"prompt_tokens": prompt_tokens,
|
||||
"eval_tokens": eval_tokens,
|
||||
"eval_duration_s": round(eval_duration_s, 2),
|
||||
"total_duration_s": round(total_duration_s, 2),
|
||||
"tokens_per_second": round(tok_s, 1),
|
||||
}
|
||||
|
||||
|
||||
def run_benchmark(
|
||||
model_name: str,
|
||||
model_size: float,
|
||||
prompt: str,
|
||||
rounds: int,
|
||||
num_predict: int,
|
||||
threshold: float = 50.0,
|
||||
) -> BenchmarkResult:
|
||||
"""Run multiple rounds and compute average."""
|
||||
results = []
|
||||
errors = []
|
||||
|
||||
for i in range(rounds):
|
||||
try:
|
||||
r = benchmark_model(model_name, prompt, num_predict)
|
||||
results.append(r)
|
||||
print(f" Round {i+1}/{rounds}: {r['tokens_per_second']} tok/s "
|
||||
f"({r['eval_tokens']} tokens in {r['eval_duration_s']}s)")
|
||||
except Exception as e:
|
||||
errors.append(str(e))
|
||||
print(f" Round {i+1}/{rounds}: ERROR - {e}")
|
||||
|
||||
if not results:
|
||||
return BenchmarkResult(
|
||||
model=model_name,
|
||||
size_gb=model_size,
|
||||
prompt_tokens=0, eval_tokens=0,
|
||||
eval_duration_s=0, tokens_per_second=0,
|
||||
total_duration_s=0, rounds=rounds,
|
||||
avg_tok_s=0, meets_threshold=False,
|
||||
error="; ".join(errors),
|
||||
)
|
||||
|
||||
avg_tok_s = sum(r["tokens_per_second"] for r in results) / len(results)
|
||||
avg_tok_s = round(avg_tok_s, 1)
|
||||
|
||||
return BenchmarkResult(
|
||||
model=model_name,
|
||||
size_gb=model_size,
|
||||
prompt_tokens=sum(r["prompt_tokens"] for r in results) // len(results),
|
||||
eval_tokens=sum(r["eval_tokens"] for r in results) // len(results),
|
||||
eval_duration_s=round(sum(r["eval_duration_s"] for r in results) / len(results), 2),
|
||||
tokens_per_second=avg_tok_s,
|
||||
total_duration_s=round(sum(r["total_duration_s"] for r in results) / len(results), 2),
|
||||
rounds=len(results),
|
||||
avg_tok_s=avg_tok_s,
|
||||
meets_threshold=avg_tok_s >= threshold,
|
||||
)
|
||||
|
||||
|
||||
def format_report(results: list[BenchmarkResult], threshold: float = 50.0) -> str:
|
||||
"""Format a human-readable benchmark report."""
|
||||
lines = []
|
||||
lines.append("")
|
||||
lines.append("=" * 72)
|
||||
lines.append(f" LOCAL MODEL BENCHMARK — {threshold:.0f} tok/s UX Threshold")
|
||||
lines.append("=" * 72)
|
||||
lines.append("")
|
||||
|
||||
# Summary table
|
||||
header = f"{'Model':<25} {'Size':>6} {'tok/s':>8} {'Threshold':>10} {'Status':>8}"
|
||||
lines.append(header)
|
||||
lines.append("-" * 72)
|
||||
|
||||
passed = 0
|
||||
failed = 0
|
||||
errors = 0
|
||||
|
||||
for r in sorted(results, key=lambda x: x.avg_tok_s, reverse=True):
|
||||
size_str = f"{r.size_gb:.1f}GB"
|
||||
tok_s_str = f"{r.avg_tok_s:.1f}"
|
||||
|
||||
if r.error:
|
||||
status = "ERROR"
|
||||
errors += 1
|
||||
elif r.meets_threshold:
|
||||
status = "PASS"
|
||||
passed += 1
|
||||
else:
|
||||
status = "FAIL"
|
||||
failed += 1
|
||||
|
||||
marker = ">" if r.meets_threshold else "X" if r.error else "!"
|
||||
thresh_str = f">= {threshold:.0f}"
|
||||
lines.append(f" {marker} {r.model:<23} {size_str:>6} {tok_s_str:>8} {thresh_str:>10} {status:>8}")
|
||||
|
||||
lines.append("-" * 72)
|
||||
lines.append(f" Passed: {passed} | Failed: {failed} | Errors: {errors} | Total: {len(results)}")
|
||||
lines.append("")
|
||||
|
||||
# Detail section for failures
|
||||
failures = [r for r in results if not r.meets_threshold and not r.error]
|
||||
if failures:
|
||||
lines.append(" FAILED MODELS (below threshold):")
|
||||
for r in sorted(failures, key=lambda x: x.avg_tok_s):
|
||||
gap = threshold - r.avg_tok_s
|
||||
lines.append(f" - {r.model}: {r.avg_tok_s:.1f} tok/s "
|
||||
f"({gap:.1f} tok/s short, {r.eval_tokens} avg tokens/round)")
|
||||
lines.append("")
|
||||
|
||||
error_list = [r for r in results if r.error]
|
||||
if error_list:
|
||||
lines.append(" ERRORS:")
|
||||
for r in error_list:
|
||||
lines.append(f" - {r.model}: {r.error}")
|
||||
lines.append("")
|
||||
|
||||
# Hardware info
|
||||
import platform
|
||||
lines.append(f" Host: {platform.node()} | {platform.system()} {platform.release()}")
|
||||
lines.append(f" Ollama: {OLLAMA_BASE}")
|
||||
lines.append("")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Benchmark local Ollama models vs 50 tok/s threshold")
|
||||
parser.add_argument("--models", help="Comma-separated model names (default: all)")
|
||||
parser.add_argument("--prompt", default=BENCHMARK_PROMPT, help="Benchmark prompt")
|
||||
parser.add_argument("--rounds", type=int, default=3, help="Rounds per model (default: 3)")
|
||||
parser.add_argument("--tokens", type=int, default=512, help="Max tokens to generate (default: 512)")
|
||||
parser.add_argument("--json", action="store_true", help="JSON output for CI")
|
||||
parser.add_argument("--all", action="store_true", help="Test all pulled models")
|
||||
parser.add_argument("--threshold", type=float, default=THRESHOLD_TOK_S, help="tok/s threshold")
|
||||
args = parser.parse_args()
|
||||
threshold = args.threshold
|
||||
|
||||
# Get model list
|
||||
available = get_models()
|
||||
if not available:
|
||||
print("No models found. Pull a model first: ollama pull <model>", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
if args.models:
|
||||
names = [m.strip() for m in args.models.split(",")]
|
||||
models = [m for m in available if m["name"] in names]
|
||||
missing = set(names) - set(m["name"] for m in models)
|
||||
if missing:
|
||||
print(f"Models not found: {', '.join(missing)}", file=sys.stderr)
|
||||
print(f"Available: {', '.join(m['name'] for m in available)}", file=sys.stderr)
|
||||
else:
|
||||
models = available
|
||||
|
||||
print(f"Benchmarking {len(models)} model(s) against {threshold} tok/s threshold")
|
||||
print(f"Ollama: {OLLAMA_BASE} | Rounds: {args.rounds} | Max tokens: {args.tokens}")
|
||||
print()
|
||||
|
||||
results = []
|
||||
for m in models:
|
||||
name = m["name"]
|
||||
size_gb = m.get("size", 0) / (1024**3)
|
||||
print(f" {name} ({size_gb:.1f}GB):")
|
||||
|
||||
result = run_benchmark(name, size_gb, args.prompt, args.rounds, args.tokens, threshold)
|
||||
results.append(result)
|
||||
|
||||
# Output
|
||||
report = format_report(results, threshold)
|
||||
if args.json:
|
||||
output = {
|
||||
"threshold_tok_s": threshold,
|
||||
"ollama_base": OLLAMA_BASE,
|
||||
"rounds": args.rounds,
|
||||
"results": [asdict(r) for r in results],
|
||||
"passed": sum(1 for r in results if r.meets_threshold),
|
||||
"failed": sum(1 for r in results if not r.meets_threshold and not r.error),
|
||||
"errors": sum(1 for r in results if r.error),
|
||||
}
|
||||
print(json.dumps(output, indent=2))
|
||||
else:
|
||||
print(report)
|
||||
|
||||
# Exit code: 0 if all pass, 1 if any fail/error
|
||||
if any(not r.meets_threshold or r.error for r in results):
|
||||
sys.exit(1)
|
||||
sys.exit(0)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,123 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Evaluate Qwen3.5:35B as a local model option for the Hermes fleet.
|
||||
|
||||
Part of Epic #281 -- Vitalik's Secure LLM Architecture.
|
||||
Issue #288 -- Evaluate Qwen3.5:35B as Local Model Option.
|
||||
|
||||
Usage:
|
||||
python3 scripts/evaluate_qwen35.py # Full evaluation
|
||||
python3 scripts/evaluate_qwen35.py --check-ollama # Check local Ollama status
|
||||
"""
|
||||
|
||||
import json, sys, time
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any, Dict
|
||||
|
||||
|
||||
@dataclass
|
||||
class ModelSpec:
|
||||
name: str = "Qwen3.5-35B-A3B"
|
||||
ollama_tag: str = "qwen3.5:35b"
|
||||
hf_id: str = "Qwen/Qwen3.5-35B-A3B"
|
||||
architecture: str = "MoE (Mixture of Experts)"
|
||||
total_params: str = "35B"
|
||||
active_params: str = "3B per token"
|
||||
context_length: int = 131072
|
||||
license: str = "Apache 2.0"
|
||||
tool_use_support: bool = True
|
||||
json_mode_support: bool = True
|
||||
function_calling: bool = True
|
||||
quantization_options: Dict[str, int] = field(default_factory=lambda: {
|
||||
"Q8_0": 36, "Q6_K": 28, "Q5_K_M": 24, "Q4_K_M": 20,
|
||||
"Q4_0": 18, "Q3_K_M": 15, "Q2_K": 12,
|
||||
})
|
||||
|
||||
|
||||
FLEET_MODELS = {
|
||||
"qwen3.5:35b (candidate)": {"params_total": "35B", "context": "128K", "local": True, "tool_use": True, "reasoning": "good"},
|
||||
"gemma4 (current local)": {"params_total": "9B", "context": "128K", "local": True, "tool_use": True, "reasoning": "good"},
|
||||
"hermes4:14b (current local)": {"params_total": "14B", "context": "8K", "local": True, "tool_use": True, "reasoning": "good"},
|
||||
"qwen2.5:7b (fleet)": {"params_total": "7B", "context": "32K", "local": True, "tool_use": True, "reasoning": "moderate"},
|
||||
"claude-sonnet-4 (cloud)": {"params_total": "?", "context": "200K", "local": False, "tool_use": True, "reasoning": "excellent"},
|
||||
"mimo-v2-pro (cloud free)": {"params_total": "?", "context": "128K", "local": False, "tool_use": True, "reasoning": "good"},
|
||||
}
|
||||
|
||||
SECURITY_CRITERIA = [
|
||||
{"criterion": "Data locality", "weight": "CRITICAL", "score": 10, "notes": "All inference local via Ollama. Zero exfiltration."},
|
||||
{"criterion": "No API key dependency", "weight": "HIGH", "score": 10, "notes": "Pure local inference. No external creds needed."},
|
||||
{"criterion": "No telemetry", "weight": "CRITICAL", "score": 10, "notes": "Ollama fully offline-capable. No phone-home."},
|
||||
{"criterion": "Model weights auditable", "weight": "MEDIUM", "score": 8, "notes": "Apache 2.0, HF SHA verification. MoE harder to audit."},
|
||||
{"criterion": "Tool-use safety", "weight": "HIGH", "score": 7, "notes": "Function calling supported, MoE routing less predictable."},
|
||||
{"criterion": "Privacy filter compat", "weight": "HIGH", "score": 9, "notes": "Local = Privacy Filter unnecessary for most queries."},
|
||||
{"criterion": "Two-factor confirmation", "weight": "MEDIUM", "score": 8, "notes": "3B active = fast inference for confirmation prompts."},
|
||||
{"criterion": "Prompt injection resistance", "weight": "HIGH", "score": 6, "notes": "3B active may be weaker. Needs red-team (#324)."},
|
||||
]
|
||||
|
||||
HARDWARE_PROFILES = {
|
||||
"mac_m2_ultra_192gb": {"name": "Mac Studio M2 Ultra (192GB)", "mem_gb": 192, "fits_q4": True, "fits_q8": True, "rec": "Q6_K", "tok_sec": 40},
|
||||
"mac_m4_pro_48gb": {"name": "Mac Mini M4 Pro (48GB)", "mem_gb": 48, "fits_q4": True, "fits_q8": False, "rec": "Q4_K_M", "tok_sec": 30},
|
||||
"mac_m1_16gb": {"name": "Mac M1 (16GB)", "mem_gb": 16, "fits_q4": False, "fits_q8": False, "rec": None, "tok_sec": None},
|
||||
"rtx_4090_24gb": {"name": "NVIDIA RTX 4090 (24GB)", "mem_gb": 24, "fits_q4": True, "fits_q8": False, "rec": "Q5_K_M", "tok_sec": 50},
|
||||
"rtx_3090_24gb": {"name": "NVIDIA RTX 3090 (24GB)", "mem_gb": 24, "fits_q4": True, "fits_q8": False, "rec": "Q4_K_M", "tok_sec": 35},
|
||||
"runpod_l40s_48gb": {"name": "RunPod L40S (48GB)", "mem_gb": 48, "fits_q4": True, "fits_q8": True, "rec": "Q6_K", "tok_sec": 60},
|
||||
}
|
||||
|
||||
|
||||
def check_ollama_status() -> Dict[str, Any]:
|
||||
import subprocess
|
||||
result = {"running": False, "models": [], "qwen35_available": False}
|
||||
try:
|
||||
r = subprocess.run(["curl", "-s", "--max-time", "5", "http://localhost:11434/api/tags"], capture_output=True, text=True, timeout=10)
|
||||
if r.returncode == 0:
|
||||
data = json.loads(r.stdout)
|
||||
result["running"] = True
|
||||
result["models"] = [m["name"] for m in data.get("models", [])]
|
||||
result["qwen35_available"] = any("qwen3.5" in m.lower() for m in result["models"])
|
||||
except Exception as e:
|
||||
result["error"] = str(e)
|
||||
return result
|
||||
|
||||
|
||||
def generate_report() -> str:
|
||||
spec = ModelSpec()
|
||||
ollama = check_ollama_status()
|
||||
lines = ["=" * 72, "Qwen3.5:35B EVALUATION REPORT -- Issue #288", "Part of Epic #281 -- Vitalik Secure LLM Architecture", "=" * 72]
|
||||
lines.append("\n## 1. Model Specification\n")
|
||||
lines.append(f" Name: {spec.name} | Arch: {spec.architecture}")
|
||||
lines.append(f" Params: {spec.total_params} total, {spec.active_params} | Context: {spec.context_length:,} tokens")
|
||||
lines.append(f" License: {spec.license} | Tool use: {spec.tool_use_support} | JSON: {spec.json_mode_support}")
|
||||
lines.append("\n## 2. VRAM Requirements\n")
|
||||
for q, vram in sorted(spec.quantization_options.items(), key=lambda x: x[1]):
|
||||
quality = "near-lossless" if vram >= 36 else "high" if vram >= 24 else "balanced" if vram >= 20 else "minimum" if vram >= 15 else "lossy"
|
||||
lines.append(f" {q:<10} {vram:>4}GB {quality}")
|
||||
lines.append("\n## 3. Hardware Compatibility\n")
|
||||
for hw in HARDWARE_PROFILES.values():
|
||||
lines.append(f" {hw['name']} {hw['mem_gb']}GB Q4:{'YES' if hw['fits_q4'] else 'NO '} Rec:{hw['rec'] or 'N/A':<8} ~{hw['tok_sec'] or 'N/A'} tok/s")
|
||||
lines.append("\n## 4. Security Evaluation (Vitalik Framework)\n")
|
||||
wm = {"CRITICAL": 3, "HIGH": 2, "MEDIUM": 1}
|
||||
tw = sum(wm[c["weight"]] for c in SECURITY_CRITERIA)
|
||||
ws = sum(c["score"] * wm[c["weight"]] for c in SECURITY_CRITERIA)
|
||||
for c in SECURITY_CRITERIA:
|
||||
lines.append(f" [{c['weight']:<8}] {c['criterion']}: {c['score']}/10 -- {c['notes']}")
|
||||
avg = ws / tw
|
||||
lines.append(f"\n Weighted score: {avg:.1f}/10 Verdict: {'STRONG' if avg >= 8 else 'ADEQUATE'}")
|
||||
lines.append("\n## 5. Fleet Comparison\n")
|
||||
for name, d in FLEET_MODELS.items():
|
||||
lines.append(f" {name:<35} {d['params_total']:<6} {d['context']:<6} {'Local' if d['local'] else 'Cloud'} {d['reasoning']}")
|
||||
lines.append("\n## 6. Ollama Status\n")
|
||||
lines.append(f" Running: {'Yes' if ollama['running'] else 'No'} | Models: {', '.join(ollama['models']) or 'none'}")
|
||||
lines.append(f" Qwen3.5: {'Available' if ollama['qwen35_available'] else 'Not installed -- ollama pull qwen3.5:35b'}")
|
||||
lines.append("\n## 7. Recommendation\n")
|
||||
lines.append(" VERDICT: APPROVED for local deployment as privacy-sensitive tier")
|
||||
lines.append("\n + Perfect data sovereignty, 128K context, Apache 2.0, MoE speed")
|
||||
lines.append(" + Tool use + JSON mode, eliminates Privacy Filter for most queries")
|
||||
lines.append(" - 20GB VRAM at Q4, MoE less predictable, needs red-team testing")
|
||||
lines.append("\n Deployment: ollama pull qwen3.5:35b -> config.yaml privacy_model")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
if "--check-ollama" in sys.argv:
|
||||
print(json.dumps(check_ollama_status(), indent=2))
|
||||
else:
|
||||
print(generate_report())
|
||||
@@ -1,46 +0,0 @@
|
||||
"""Tests for Qwen3.5:35B evaluation -- Issue #288."""
|
||||
import pytest
|
||||
from scripts.evaluate_qwen35 import ModelSpec, FLEET_MODELS, SECURITY_CRITERIA, HARDWARE_PROFILES, check_ollama_status, generate_report
|
||||
|
||||
class TestModelSpec:
|
||||
def test_fields(self):
|
||||
s = ModelSpec()
|
||||
assert s.name == "Qwen3.5-35B-A3B"
|
||||
assert s.context_length == 131072
|
||||
assert s.license == "Apache 2.0"
|
||||
assert s.tool_use_support is True
|
||||
def test_quant_vram_decreasing(self):
|
||||
s = ModelSpec()
|
||||
items = sorted(s.quantization_options.items(), key=lambda x: x[1])
|
||||
for i in range(1, len(items)):
|
||||
assert items[i][1] >= items[i-1][1]
|
||||
|
||||
class TestSecurity:
|
||||
def test_scores(self):
|
||||
for c in SECURITY_CRITERIA:
|
||||
assert 1 <= c["score"] <= 10
|
||||
def test_weighted_avg(self):
|
||||
wm = {"CRITICAL": 3, "HIGH": 2, "MEDIUM": 1}
|
||||
tw = sum(wm[c["weight"]] for c in SECURITY_CRITERIA)
|
||||
ws = sum(c["score"] * wm[c["weight"]] for c in SECURITY_CRITERIA)
|
||||
assert ws / tw >= 7.0
|
||||
|
||||
class TestHardware:
|
||||
def test_m2_fits(self):
|
||||
assert HARDWARE_PROFILES["mac_m2_ultra_192gb"]["fits_q4"] is True
|
||||
def test_m1_no(self):
|
||||
assert HARDWARE_PROFILES["mac_m1_16gb"]["fits_q4"] is False
|
||||
|
||||
class TestReport:
|
||||
def test_sections(self):
|
||||
r = generate_report()
|
||||
for s in ["Model Specification", "VRAM", "Hardware", "Security", "Fleet", "Recommendation"]:
|
||||
assert s in r
|
||||
def test_approved(self):
|
||||
assert "APPROVED" in generate_report()
|
||||
|
||||
class TestOllama:
|
||||
def test_returns_dict(self):
|
||||
r = check_ollama_status()
|
||||
assert isinstance(r, dict)
|
||||
assert "running" in r
|
||||
Reference in New Issue
Block a user