HERALD enables near-lossless accuracy at 5-10% KV budget for block dLLMs by amortizing top-k selection across denoising steps and overlapping CPU-GPU retrieval, yielding up to 2.47x higher throughput than GPU-only inference.
arXiv preprint arXiv:2510.11292 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
EntropyInfer adaptively allocates inference compute using per-head attention entropy for rigid/dynamic classification during prefilling and compresses KV cache with generated tokens, achieving up to 2.39x speedup on long contexts.
PRR accelerates dynamic sparse attention decoding in long-context LLMs via EMA-based prediction, speculative attention, and FlashAttention repair, achieving up to 40% latency reduction.
citing papers explorer
-
HERALD: High-Throughput Block Diffusion LLM Serving via CPU-GPU Cooperative KV Cache Retrieval
HERALD enables near-lossless accuracy at 5-10% KV budget for block dLLMs by amortizing top-k selection across denoising steps and overlapping CPU-GPU retrieval, yielding up to 2.47x higher throughput than GPU-only inference.
-
From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs
EntropyInfer adaptively allocates inference compute using per-head attention entropy for rigid/dynamic classification during prefilling and compresses KV cache with generated tokens, achieving up to 2.39x speedup on long contexts.
-
Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding
PRR accelerates dynamic sparse attention decoding in long-context LLMs via EMA-based prediction, speculative attention, and FlashAttention repair, achieving up to 40% latency reduction.