Prefilling-dLLM partitions prefixes into chunks, caches KV representations, and applies sparse top-K selection during decoding to cut dLLM inference complexity to quadratic in decode length only.
arXiv preprint arXiv:2504.19867 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 2
citation-polarity summary
years
2026 4roles
method 2polarities
use method 2representative citing papers
KVServe delivers up to 9.13x job completion time speedup and 32.8x time-to-first-token reduction by making KV cache compression service-aware and adaptive in disaggregated LLM serving.
FlexNPU is a transparent virtualization system for Ascend NPUs that supports dynamic prefill-decode co-location in LLM serving and reports throughput gains plus large TTFT reductions versus static baselines.
A survey synthesizing challenges, system architectures, model optimizations, deployment methods, and resource management techniques for large language model inference at the network edge.
citing papers explorer
-
Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models
Prefilling-dLLM partitions prefixes into chunks, caches KV representations, and applies sparse top-K selection during decoding to cut dLLM inference complexity to quadratic in decode length only.
-
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
KVServe delivers up to 9.13x job completion time speedup and 32.8x time-to-first-token reduction by making KV cache compression service-aware and adaptive in disaggregated LLM serving.
-
FlexNPU: Transparent NPU Virtualization for Dynamic LLM Prefill-Decode Co-location
FlexNPU is a transparent virtualization system for Ascend NPUs that supports dynamic prefill-decode co-location in LLM serving and reports throughput gains plus large TTFT reductions versus static baselines.
-
Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities
A survey synthesizing challenges, system architectures, model optimizations, deployment methods, and resource management techniques for large language model inference at the network edge.