왜 90% 컨텍스트가 정직한 벤치마크인가

#!/usr/bin/env python3
"""Decode and TTFT at fractions of a context window. Build a prompt of the
target token count, generate, and record what mlx-lm reports. This is the
`curve` experiment of silicon_lab.py, trimmed to its essentials."""
import sys, time
import mlx.core as mx
from mlx_lm import load, stream_generate
from mlx_lm.sample_utils import make_sampler

repo = sys.argv[1] if len(sys.argv) > 1 else "mlx-community/Qwen3.5-9B-4bit"
window = int(sys.argv[2]) if len(sys.argv) > 2 else 32768
FILLER = "Decode re-reads the weights for every generated token, which is why its ceiling is bandwidth divided by bytes per token. "
QUESTION = "Explain the passage in detail, in at least 400 words."

model, tok = load(repo)


def prompt_of(target: int) -> list[int]:
    reps = max(1, target // 24)                          # ~24 tokens per filler sentence
    ids = tok.apply_chat_template([{"role": "user", "content": FILLER * reps + QUESTION}], add_generation_prompt=True)
    while len(ids) > target and reps > 1:
        reps -= 1
        ids = tok.apply_chat_template([{"role": "user", "content": FILLER * reps + QUESTION}], add_generation_prompt=True)
    return ids


for frac in (0.1, 0.5, 0.9):
    ids = prompt_of(int(window * frac))
    mx.reset_peak_memory(); t0 = time.perf_counter(); first = None
    for r in stream_generate(model, tok, ids, max_tokens=200, sampler=make_sampler(temp=0.0)):
        if first is None:
            first = time.perf_counter() - t0
    print(f"{frac:.0%} of {window}: prompt {r.prompt_tokens:6d}  TTFT {first:6.2f}s  prefill {r.prompt_tps:7.1f} tok/s  "
          f"decode {r.generation_tps:6.2f} tok/s  peak {r.peak_memory:5.2f} GB")

# office, mlx 0.32.2, 2026-09-15, Qwen3.5-9B-4bit:
# 10%: prompt 3233  TTFT  2.69s  prefill 1277  decode 94.38  peak 6.77
# 50%: prompt 16337 TTFT 13.12s  prefill 1259  decode 86.31  peak 8.13
# 90%: prompt 29385 TTFT 24.90s  prefill 1187  decode 78.10  peak 9.39