botp
/

Solomon / mlx /src /solomon_mlx /artifacts.py
orz99's picture ArcherHume's picture
Duplicate from DoccyHealth/Solomon
1d2de8a
Raw
History Blame Contribute Delete
2.61 kB
"""Artifact verification and distinct MLX runtime identities."""
import hashlib
import json
from importlib.metadata import version
from pathlib import Path
SOLOMON_REVISION = "5c0a4a82ddaeca6da2e3013f7045a8196c86957d"
BASE_REVISION = "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0"
ADAPTER_SHA = "2addaf841ecc58829ad73081603b8d3e52743c53c6d558a17a1dd30e9bd2dbca"
HEADS_SHA = "126a9b5487dca937a768a4f228f2d2e7d513900d8ad0e99c4137fbaa42a1aa6f"
def sha256(path):
h = hashlib.sha256()
with Path(path).open("rb") as f:
for block in iter(lambda: f.read(8 << 20), b""):
h.update(block)
return h.hexdigest()
def digest(value):
return hashlib.sha256(
json.dumps(value, sort_keys=True, separators=(",", ":"), allow_nan=False).encode()
).hexdigest()
def verify_release(root):
root = Path(root)
manifest = json.loads((root / "MANIFEST.json").read_text())
checked = {}
for row in manifest["files"]:
rel = row["destination"]
path = (root / rel).resolve()
if not path.is_relative_to(root.resolve()):
raise ValueError("Manifest path escapes source directory")
expected = row.get("staged_sha256")
size = row.get("staged_bytes")
actual = sha256(path)
if expected and actual != expected:
raise ValueError(f"Source checksum mismatch: {rel}")
if size is not None and path.stat().st_size != size:
raise ValueError(f"Source size mismatch: {rel}")
checked[rel] = actual
return checked
def code_identity():
root = Path(__file__).parent
return digest({str(p.relative_to(root)): sha256(p) for p in sorted(root.rglob("*.py"))})
def runtime_identity(binding, *, chunk_size=2048, max_tokens=40960):
import platform
import mlx.core as mx
value = {
"backend": "mlx-metal",
"contract": "solomon-mlx-v1",
"source_contract": "solomon-v1",
"profile": binding["profile"],
"chunk_size": chunk_size,
"max_tokens": max_tokens,
"metal_device": mx.device_info(),
"macos_version": platform.mac_ver()[0],
"model_binding": digest(binding),
"code_sha256": code_identity(),
"versions": {p: version(p) for p in ("mlx", "mlx-vlm", "transformers", "numpy", "pillow")},
"placement": "question",
"lora_scale": 2.0,
"answer_projection": "trained-semantic-head-float32",
"recurrence": "mlx-float32",
"solomon_revision": SOLOMON_REVISION,
"base_revision": BASE_REVISION,
}
return {**value, "fingerprint": digest(value)}