arXiv:2512.16391v2 Announce Type: replace-cross Abstract: Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG...
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.
arXiv:2608. 19758v1 Announce Type: new Abstract: Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase.
arXiv:2606. 13392v1 Announce Type: new Abstract: Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale.
arXiv:2508. 18224v3 Announce Type: replace-cross Abstract: Recent advances in sparse attention mechanisms have demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs).
arXiv:2607. 22583v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities.
arXiv:2607. 07953v1 Announce Type: cross Abstract: Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length limits training and inference at long context.
arXiv:2605.23200v2 Announce Type: replace-cross Abstract: The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate t...
arXiv:2605. 01910v2 Announce Type: replace-cross Abstract: Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all $n_k$ key and value vectors from KV cache.
arXiv:2607. 21985v1 Announce Type: cross Abstract: The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost.
arXiv:2606. 06467v1 Announce Type: cross Abstract: Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially in reasoning-heavy settings where models generate long intermediate chains of thought.
UniPrefill is a prefill‑acceleration framework that works with virtually any model architecture, directly speeding up token‑level computation. It is implemented as a continuous‑batching operator and extends vLLM’s scheduling to support prefill‑decode co‑processing and tensor parallelism. The method delivers up to a 2.1× speedup in Time‑to‑First‑Token, with gains growing as concurrent requests increase.