arXiv Machine Learning
Jun 24
RoPE-Aware Bit Allocation for KV-Cache Quantization
arXiv:2606. 24033v1 Announce Type: new Abstract: Existing low-bit KV-cache quantizers often treat each cached key as a flat vector.
UltraQuant: 4-bit KV Caching for Context-Heavy Agents
arXiv:2606. 20474v1 Announce Type: cross Abstract: Context-heavy agents place unusual pressure on the key-value (KV) cache: long prefixes are reused across many short turns, while concurrency determines whether the serving system can keep GPUs utilized.
Related stories
arXiv AI
Aug 26
Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention
Minima-KV introduces a retention‑preserving hierarchy for mixed‑format paged attention that keeps recent and protected anchor pages in FP8 while older pages are compressed into packed TQ3, allowing every live‑request page to remain addressable. The approach uses format‑specific kernels and a globally normalized online‑softmax merge to compute partial attention states, enabling direct heterogeneous decoding without a dense shadow cache. Experiments on Qwen3.6‑27B on a 96‑GB NVIDIA RTX PRO 6000 Blackwell GPU show 3.50× compression over BF16 and 1.75× over FP8, with minimal impact on performance across long‑context benchmarks.
arXiv Machine Learning
Aug 11
RotaryQuant: Fitting 120B MoE Models on Consumer Hardware via Fused Compressed-Space Attention
arXiv:2608. 08081v1 Announce Type: cross Abstract: Large mixture-of-experts (MoE) language models with 26--120 billion parameters exceed the memory capacity of consumer devices through three simultaneous pressures: resident weight matrices, key-value (KV) cache state that grows linearly with context, and dozens of expert sublayers that must be paged on demand.
arXiv Machine Learning
Jul 2
MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression
arXiv:2607. 00760v1 Announce Type: new Abstract: Long-context LLM services now sustain prompts with hundreds of thousands to millions of tokens, making the key-value (KV) cache a first-order serving cost.
arXiv Machine Learning
Sep 15
Physically Partitioned KVCache Format for CPU--GPU Load Balancing in MoE Inference
arXiv:2609.14507v1 Announce Type: cross Abstract: Single-GPU long-context inference with Mixture-of-Experts (MoE) models requires spilling the key-value cache (KVCache) to CPU memory. The spilled KV...
arXiv AI
Sep 16
Where Should the KV Cache Live? Placement Policies Across GPU, CPU, and SSD for Long-Lived Sessions
arXiv:2609.16215v1 Announce Type: new Abstract: GPU high bandwidth memory is scarce and expensive, and KV caches consume much of it as chats, agent loops, and document question answering accumulate s...
arXiv AI
Aug 10
Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference
arXiv:2604. 26968v2 Announce Type: replace-cross Abstract: Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving.
arXiv Machine Learning
5d ago
The KV Cache Is the New Memory Wall
The paper argues that for large‑context autoregressive language‑model inference, memory bandwidth—specifically the Key‑Value (KV) cache—becomes the limiting resource rather than arithmetic throughput. It analytically derives how arithmetic intensity decays with context length for NVIDIA H100, NVIDIA B200, and AMD MI300X, identifies crossover points where KV traffic overtakes weight traffic, and evaluates representative techniques across five compression domains. The study finds a three‑regime behavior: below the crossover, weight traffic dominates and KV compression offers little benefit; beyond it, KV traffic dominates and compression methods trade quality for bandwidth, with paging and prefix sharing being lossless but capacity‑limited, while quantization and eviction directly reduce bandwidth at the cost of accuracy. whyItMatters":"The work provides a unified analytical framework and a standardized protocol that enable consistent comparison of KV‑compression techniques across hardware and workloads, guiding practitioners in selecting appropriate methods for long‑context inference."
arXiv Machine Learning
Sep 17
Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches
arXiv:2609.17652v1 Announce Type: new Abstract: When agentic sessions run to a million tokens with many sessions resident at once, the KV cache and the index that ranks it live in host memory, and th...
arXiv Machine Learning
Jun 3
Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving
arXiv:2606. 02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation.
arXiv AI
Jun 12
MiniPIC: Flexible Position-Independent Caching in <100LOC
arXiv:2606. 13126v1 Announce Type: cross Abstract: Retrieval-augmented and agentic workloads repeatedly prefill recurring predictable structured inputs (which we call "spans") such as documents and code files.
arXiv Machine Learning
Aug 21
CacheRoute: Planned Prefix-Affinity Routing for Large-Scale LLM Serving
arXiv:2608. 19677v1 Announce Type: cross Abstract: Prefix caching avoids prefill only when a repeated request returns to a server that still holds the prefix KV.