完整的引擎

def step(self) -> list[Output]:
    # 1. SCHEDULE — who runs, and with what token budget       (S10, S11)
    batch = self.scheduler.schedule()
    if not batch:
        return []

    # 2. MEMORY — resolve prefix hits, then allocate blocks    (S06, S07)
    for req in batch.new_requests:
        reused, start = self.prefix_cache.match(req.token_ids)
        req.block_table = reused + self.blocks.allocate(req, from_token=start)

    # 3. PROPOSE — optional draft tokens for verification      (S14)
    if self.spec_enabled and batch.is_decode_only:
        batch = self.proposer.attach_drafts(batch, k=self.adaptive_k())

    # 4. EXECUTE — one forward pass over a ragged batch        (S03, S12, S13)
    runner = self.graph_runner if batch.can_use_graph else self.eager_runner
    logits = runner.forward(batch)

    # 5. SAMPLE — per-request params, grammar masks, verify    (S04, S15, S14)
    tokens = self.sampler.sample(logits, batch.sampling_metadata)
    tokens = self.verifier.accept(tokens, batch)     # no-op without speculation

    # 6. RETIRE — stop checks, free blocks, publish to streams (S19)
    return self.postprocess(batch, tokens)

def ablate(workload, features):
    """Turn one feature off at a time and measure what it was worth."""
    baseline = benchmark(Engine(**features), workload)
    rows = []

    for name in features:
        reduced = {**features, name: False}
        result = benchmark(Engine(**reduced), workload)
        rows.append((name, baseline.throughput / result.throughput))

    return sorted(rows, key=lambda r: -r[1])   # most valuable first