KV-Caches
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Announce Type: new Abstract: Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon decoding, as the KV-cache grows. KV-cache quantization can help improve this, but current methods are evaluated under prefill-like settings and errors behave differently under autoregressive decoding. We show that in the latter regime, quantization errors accumulate across timesteps, driven primarily by incorrect...
KVarN: Native vLLM backend for KV-cache quantization by Huawei
⚡️ Built for agentic and long-context workloads. 💡 KVarN delivers 3-5x more KV-cache capacity and up to ~1.3x the throughput of FP16, so you fit far longer contexts and serve more concurrent requests, with FP16-level accuracy. 🔌 Calibration-free, plug-and-play with vLLM.
ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
arXiv:2602.07721v3 Announce Type: replace Abstract: KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale. We introduce ParisKV, a drift-robust, GPU-native KV-cache retrieval framework based on collision-based candidate selection, followed by a quantized inner-product reranking estimator. For million-token contexts, ParisKV supports CPU-offloaded KV caches via Unified Virtual Addressing (UVA), enabling...
Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving
Announce Type: new Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation. While approximate KV cache retention techniques reduce memory usage by sacrificing model accuracy, lossless approaches instead evict KV cache blocks from GPU memory and reconstruct them on demand to preserve exact outputs. Existing lossless KV cache management systems primarily base eviction decisions on access frequency or positional heuristics, without...
Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems
Announce Type: replace Abstract: Rowhammer on GPU DRAM has enabled adversarial bit flips in model weights; shared KV-cache blocks in LLM serving systems present an analogous but previously unexamined target. In vLLM's Prefix Caching, these blocks exist as a single physical copy without integrity protection. Using software fault injection under ideal bit targeting, we characterize worst-case severity and identify three properties: (1) Silent divergence - 13 of 16 BF16 bit positions produce...
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
Announce Type: new Abstract: Large language models (LLMs) with extended context lengths rely on the key-value (KV) cache to support attention over prior tokens. However, maintaining the KV cache incurs substantial memory overhead, motivating KV-cache compression methods that enforce a fixed budget through eviction and merging. Modern eviction methods increasingly adopt span-based retention because preserving contiguous spans is empirically effective and better preserves semantic coherence.
STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models
Announce Type: new Abstract: Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps. For instance, UI-TARS-1.5-7B consumes 76 GB of GPU memory on merely five screenshots, approaching the capacity of mainstream 80 GB accelerators. Existing KV compression methods share two structural assumptions: aggregating visual-token importance into a...
Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifold
Announce Type: replace Abstract: Key-value (KV) caching enables fast autoregressive decoding but at long contexts becomes a dominant bottleneck in High Bandwidth Memory (HBM) capacity and bandwidth. A common mitigation is to compress cached keys and values by projecting per-head matrices to a lower rank, storing only the projections in the HBM. However, existing post-training approaches typically fit these projections using SVD-style proxy objectives, which may poorly reflect end-to-end...
AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving
Announce Type: new Abstract: Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution. Serving these workloads requires scheduling, KV-cache management, and routing policies that use program-level context, including turn dependencies, tool-induced gaps, and reusable KV state. Evaluating such policies directly on real systems is costly, since each design point may require dedicated accelerator...
AURA: Action-Gated Memory for Robot Policies at Constant VRAM
Announce Type: new Abstract: The KV-cache is the right memory for datacenters but the wrong memory for robots. Datacenter inference batches many short requests and resets them, amortizing an attention cache across a crowd. Embodied agents instead run one long, non-resetting episode on bandwidth-limited edge hardware, where high-bandwidth memory and flash are scarce, flash has finite write endurance, and memory writes rather than compute can become the binding constraint.