vllm.models.deepseek_v41.nvidia.ops.candidate_indexer
¶
DSV4.1 candidate-only prefill and decode over the paged indexer cache.
Classes:
-
CandidatePlan–One step's row bounds and sorted candidates, shared by consumer layers.
CandidatePlan
dataclass
¶
One step's row bounds and sorted candidates, shared by consumer layers.