vllm.model_executor.warmup.step5_dsa_warmup
¶
Warm Step5 DSA scored prefill before serving.
Startup dummy runs are short, so every row selects its whole history and the indexer scoring path (summary packing, FP8 logits, top-k, page metadata and, for multi-group caches, staged prefill pages) would otherwise JIT on the first prefill longer than top-k regions. Under DP every rank stalls on that rank.