Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

OasisKV: Boosting LLM Throughput by Prefetching Sparse KV Caches Beyond HBM

AI By Crimson AI Hugging Face Papers 11 August 2026 · 00:00 12 views
Share: X Telegram

OasisKV, a new memory-centric inference system from Hugging Face researchers, stores full KV caches in cheaper memory tiers and uses speculative decoding to prefetch only the most relevant entries into HBM, achieving up to 2.1x throughput gains over dense vLLM with minimal accuracy loss.

OasisKV: Boosting LLM Throughput by Prefetching Sparse KV Caches Beyond HBM

Key points

As large language models (LLMs) handle longer contexts and more complex reasoning, the key-value (KV) cache has become a major bottleneck, consuming both memory capacity and bandwidth during token generation. High-bandwidth memory (HBM), though fast, is expensive and limited, constraining batch sizes and overall throughput. A new paper from Hugging Face researchers introduces OasisKV, a system designed to break this memory ceiling.

OasisKV takes a memory-centric approach: instead of keeping the entire KV cache in HBM, it stores the full cache in lower-cost memory tiers (such as host or remote memory) and only brings the most relevant entries into HBM for attention computation. This is possible because attention during decoding is naturally sparse—only a small subset of tokens truly matters for each step.

The key innovation is using speculative decoding to predict which tokens will be important in the next step. By drafting lookahead tokens, OasisKV can accurately identify and prefetch the necessary KV blocks ahead of time, staging them in HBM before they are needed. This lookahead prediction is so precise that it maintains accuracy within 0.7 points of full attention when operating under a 2,048-token KV budget.

Built on vLLM, OasisKV demonstrates significant throughput gains: 1.69x over dense vLLM on reasoning workloads with only 0.1 points of accuracy loss, and up to 2.1x on multi-GPU long-context serving. In prefill-decode disaggregation scenarios, it achieves about 2x dense throughput while admitting each request with 6.5–9.7x less KV and holding 2.2–2.6x less decode-node host memory than full KV transfer.

The paper concludes that OasisKV effectively expands the in-decode memory capacity by leveraging off-GPU memory, offering a practical path to scale LLM inference without being hamstrung by HBM limitations.

MetricOasisKV vs. Dense vLLM
Throughput (reasoning workload)1.69x (0.1 points accuracy loss)
Throughput (multi-GPU long-context)Up to 2.1x
Throughput (prefill-decode disaggregation)~2x
KV per request (disaggregation)6.5–9.7x less
Decode-node host memory (disaggregation)2.2–2.6x less
Accuracy (2,048-token KV budget)Within 0.7 points of full attention
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1