File size: 8,068 Bytes
db536d3 28868a6 db536d3 b3106d8 db536d3 c953041 db536d3 b3106d8 db536d3 b3106d8 db536d3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 | """
Build and verify every named (bits, memory_profile) variant.
Outputs:
variants/neural_alu{8,16,32}.safetensors - no memory
variants/neural_computer{8,16,32}_registers.safetensors - 16 B
variants/neural_computer{8,16,32}_scratchpad.safetensors - 256 B
variants/neural_computer{8,16,32}_small.safetensors - 1 KB
variants/neural_computer{8,16,32}_reduced.safetensors - 4 KB
variants/neural_computer{8,16,32}.safetensors - 64 KB
Each variant is built from the canonical seed, quantized to minimum
integer dtypes with the strict ternary check (--ternary --strict), and
then verified with eval.py via the BatchedFitnessEvaluator; the summary
records (tensor count, params, file size, fitness, total_tests, seconds).
"""
from __future__ import annotations
import os
import shutil
import subprocess
import sys
import time
from pathlib import Path
import torch
from safetensors import safe_open
ROOT = Path(__file__).resolve().parent.parent # repo root (this file lives in tools/)
SEED = ROOT / "neural_computer.safetensors"
OUT_DIR = ROOT / "variants"
OUT_DIR.mkdir(exist_ok=True)
PROFILES = ["none", "registers", "scratchpad", "small", "reduced", "full"]
BITS = [8, 16, 32]
def variant_filename(bits: int, profile: str) -> str:
if profile == "none":
return f"neural_alu{bits}.safetensors"
if profile == "full":
return f"neural_computer{bits}.safetensors"
return f"neural_computer{bits}_{profile}.safetensors"
def run(cmd: list[str], timeout: int = 600) -> tuple[int, str]:
p = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
return p.returncode, (p.stdout or "") + (p.stderr or "")
def build_variant(bits: int, profile: str) -> Path:
out = OUT_DIR / variant_filename(bits, profile)
shutil.copy2(SEED, out)
cmd = [
sys.executable, str(ROOT / "src" / "build.py"),
"--bits", str(bits),
"-m", profile,
"--apply",
"--model", str(out),
"all",
]
rc, log = run(cmd, timeout=2400)
if rc != 0:
raise RuntimeError(f"build failed for bits={bits} profile={profile}:\n{log[-1500:]}")
return out
def quantize_variant(path: Path) -> tuple[int, int]:
"""Run quantize.py --ternary --strict on a built variant. This is the
last pipeline step: it casts every tensor to its minimum signed integer
dtype, verifies the strictly ternary weight invariant, and stamps the
weight_quantization metadata field. Returns (bytes_before, bytes_after).
"""
rc, log = run([sys.executable, str(ROOT / "src" / "quantize.py"), str(path),
"--ternary", "--strict"], timeout=300)
if rc != 0:
raise RuntimeError(f"quantize failed for {path.name}:\n{log[-800:]}")
# parse the "file X.X MB -> Y.Y MB" line
for line in log.splitlines():
if "file" in line and "->" in line and path.name in line:
try:
parts = line.split("file")[1].split("->")
before = float(parts[0].strip().split()[0]) * 1e6
after = float(parts[1].strip().split()[0]) * 1e6
return int(before), int(after)
except Exception:
pass
return 0, 0
def measure_variant(path: Path) -> dict:
"""Read tensor count, params, manifest values from the variant."""
with safe_open(str(path), framework="pt") as f:
keys = list(f.keys())
params = sum(f.get_tensor(k).numel() for k in keys)
manifest = {
k.split(".", 1)[1]: f.get_tensor(k).item()
for k in keys if k.startswith("manifest.") and f.get_tensor(k).numel() == 1
}
return {
"tensors": len(keys),
"params": params,
"size_mb": path.stat().st_size / (1024 * 1024),
"manifest": manifest,
}
def eval_variant(path: Path, device: str = "cpu", timeout: int = 600) -> dict:
"""Run eval.py against a variant and parse fitness."""
cmd = [
sys.executable, str(ROOT / "src" / "eval.py"),
"--model", str(path),
"--device", device,
"--quiet",
]
t0 = time.time()
rc, log = run(cmd, timeout=timeout)
dt = time.time() - t0
fitness = None
total_tests = None
status = "ERROR"
for line in log.splitlines():
line = line.strip()
if line.startswith("Fitness:"):
try:
fitness = float(line.split()[1])
except Exception:
pass
elif line.startswith("Total tests:"):
try:
total_tests = int(line.split()[2])
except Exception:
pass
elif line.startswith("STATUS:"):
status = line.split()[1]
return {
"rc": rc,
"fitness": fitness,
"total_tests": total_tests,
"status": status,
"elapsed_s": dt,
"log_tail": "\n".join(log.splitlines()[-15:]),
}
def main() -> None:
rows = []
print(f"Building 18 variants into {OUT_DIR}\n")
for bits in BITS:
for profile in PROFILES:
label = f"bits={bits} profile={profile}"
print(f"=== {label} ===", flush=True)
t0 = time.time()
try:
path = build_variant(bits, profile)
bt = time.time() - t0
pre_q_meta = measure_variant(path)
# Quantize in-place as the final step; weights are
# integer-valued so this is exact, --strict fails the build
# if any weight is non-ternary, and header metadata
# (signal_registry) is carried through.
qb, qa = quantize_variant(path)
meta = measure_variant(path)
ev = eval_variant(path, device="cpu", timeout=900)
rows.append({
"bits": bits, "profile": profile,
"filename": path.name,
"build_s": bt,
**meta,
**{k: ev[k] for k in ("fitness", "total_tests", "status", "elapsed_s")},
"log_tail": ev["log_tail"] if ev["status"] != "PASS" else "",
})
q_ratio = qb / qa if qa else 1.0
print(f" built in {bt:.1f}s size={pre_q_meta['size_mb']:.1f}MB -> "
f"{meta['size_mb']:.1f}MB after quant ({q_ratio:.2f}x)"
f" params={meta['params']:,} tensors={meta['tensors']:,}")
print(f" eval: fitness={ev['fitness']} tests={ev['total_tests']}"
f" status={ev['status']} ({ev['elapsed_s']:.1f}s)")
if ev["status"] != "PASS":
print(" --- failure tail ---")
print(" " + "\n ".join(ev["log_tail"].splitlines()))
print(" --------------------")
except Exception as e:
print(f" EXCEPTION: {e}")
rows.append({"bits": bits, "profile": profile, "error": str(e)})
print()
print("=" * 88)
print(" SUMMARY")
print("=" * 88)
header = f"{'bits':>4} {'profile':<11} {'size_MB':>8} {'tensors':>8} {'params':>11} {'fitness':>9} {'tests':>6} {'status':>7}"
print(header)
print("-" * len(header))
for r in rows:
if "error" in r:
print(f"{r['bits']:>4} {r['profile']:<11} ERROR: {r['error'][:60]}")
continue
fit = f"{r['fitness']:.4f}" if r['fitness'] is not None else "n/a"
tests = r['total_tests'] if r['total_tests'] is not None else "?"
print(f"{r['bits']:>4} {r['profile']:<11} {r['size_mb']:>8.1f} "
f"{r['tensors']:>8,} {r['params']:>11,} "
f"{fit:>9} {tests:>6} {r['status']:>7}")
fail = [r for r in rows if r.get("status") != "PASS" or "error" in r]
print()
if fail:
print(f"FAILURES: {len(fail)}/{len(rows)}")
else:
print(f"ALL {len(rows)} VARIANTS PASS")
if __name__ == "__main__":
main()
|