Pith. sign in

REVIEW 1 cited by

Inference-Friendly Models With MixAttention

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.15012 v1 pith:Y5ZIKANF submitted 2024-09-23 cs.CL cs.AI

classification cs.CLcs.AI
keywords cachemixattentioninferenceacrossarchitectureattentionexplorememory
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The size of the key-value (KV) cache plays a critical role in determining both the maximum context length and the number of concurrent requests supported during inference in modern language models. The KV cache size grows proportionally with the number of attention heads and the tokens processed, leading to increased memory consumption and slower inference for long inputs. In this work, we explore the use of MixAttention, a model architecture modification closely related to a blog published by Character.AI. MixAttention combines sliding window attention, where only a small subset of recent tokens is stored in the KV cache, with KV cache sharing across layers. Our experiments demonstrate that MixAttention significantly reduces memory usage and improves inference speed without sacrificing model performance in both short and long-context tasks. We also explore various configurations of this architecture, identifying those that maintain quality across evaluation metrics while optimizing resource efficiency.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference

    cs.LG 2025-08 conditional novelty 5.0 of 10

    TPLA splits the latent KV cache across tensor-parallel GPUs while keeping every head's full view, yielding 1.79x and 1.93x decode speedups on DeepSeek-V3 and Kimi-K2 at 32K context with modest accuracy loss.

Pith tools