디스크의 파일에서 통합 메모리 페이지로

#!/usr/bin/env python3
"""Watch a checkpoint become memory. vm_stat before, after load (lazy: mapped,
not yet touched), and after the first forward pass (pages touched and wired
for the GPU). Sizes in GiB from 16 KB pages."""
import subprocess, time
import mlx.core as mx
from mlx_lm import load

PAGE = 16384


def vm() -> dict:
    out = subprocess.run(["vm_stat"], capture_output=True, text=True).stdout
    return {line.split(":")[0].strip(): int(line.split(":")[1].strip().rstrip("."))
            for line in out.splitlines()[1:] if ":" in line}


def gib(pages: int) -> float:
    return pages * PAGE / 2**30


before = vm()
t = time.perf_counter(); model, tok = load("mlx-community/Qwen3.5-27B-4bit"); t_load = time.perf_counter() - t
after_load = vm()
prompt = mx.array(tok.apply_chat_template([{"role": "user", "content": "hi"}], add_generation_prompt=True))[None]
t = time.perf_counter(); mx.eval(model(prompt)); t_first = time.perf_counter() - t
after_first = vm()

for name, snap in (("before", before), ("after load()", after_load), ("after first forward", after_first)):
    print(f"{name:20} wired {gib(snap['Pages wired down']):7.2f} GiB   active {gib(snap['Pages active']):7.2f} GiB   free {gib(snap['Pages free']):7.2f} GiB")
print(f"\nload() {t_load:.2f}s (lazy: mapped, not read)   first forward {t_first:.2f}s (pages touched, wired)")
print(f"MLX active memory after first forward: {mx.get_active_memory()/2**30:.2f} GiB")

# office, M3 Ultra, 2026-09-15 (warm):
# before               wired  29.28   active 199.50   free 79.51
# after load()         wired  27.02   active 213.25   free 52.91     load() 3.71s
# after first forward  wired  43.41   active 198.31   free 51.60     first forward 1.27s; MLX active 14.09 GiB

# first 8 bytes: header length; then the JSON header naming every tensor and its byte range
f=~/.cache/huggingface/hub/models--mlx-community--Qwen3.5-27B-4bit/snapshots/*/model-00001-of-*.safetensors
python3 - "$f" <<'PY'
import json, struct, sys, glob
path = glob.glob(sys.argv[1])[0]
with open(path, "rb") as fh:
    n = struct.unpack("<Q", fh.read(8))[0]
    header = json.loads(fh.read(n))
print(f"{len(header)} tensors in this shard; header {n/1024:.0f} KB")
name, meta = next((k, v) for k, v in header.items() if k != "__metadata__")
print(name, meta["dtype"], meta["shape"], "bytes", meta["data_offsets"][1] - meta["data_offsets"][0])
PY
# office, 2026-09-15: 848 tensors in this shard; header 102 KB
# language_model.model.embed_tokens.biases BF16 [248320, 80] bytes 39731200