V Cache coverage.

Still: Amortized KV Cache Compaction in a Single Forward Pass

The KV cache is the memory bottleneck of long-horizon language model deployment. Practically, a deployable compactor must be lightweight enough to call during inference, expressive…

Xcena, whose MX1 chip performs data orchestration and KV cache management directly within memory modules, raised a $135M Series B at a $570M valuation (Kate Park/TechCrunch)

New Silicon Motion SM2524XT chip brings 14 GB/s to mainstream SSDs — 6nm DRAMless controller boasts heavy AI PC optimization and slashes KV cache latency

Fast, furious, inexpensive.…

KV-Pool: 4.5x Agent Inference Throughput with Persistent KV Cache

Why Agent Workloads Are Expensive LLM inference costs always scale with context length. In...…

Shard - getting to 10× KV cache compression

(Yet Another) KV cache calculator - kvanta.vcerny.cz

OSCAR RotationZoo - Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization

ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse

Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the …

DeepSeek-V4 KV Cache Explained: Why 1M Context Uses Less VRAM

A comparison of DeepSeek-V4's CSA/HCA hybrid compressed attention with traditional MHA, GQA, and MLA, explaining why DeepSeek-V4 can greatly reduce KV Cache memory for 1M-token con…

llama.cpp has a clever trick for speeding up KV cache decode

Show HN: KVBoost – chunk-level KV cache reuse for HuggingFace, 5–48x faster TTFT

KV Cache Explained Like You're an LLM Engineer

How transformer inference actually works under the hood — and why KV cache is the single most...…

Quantizing MTP KV Cache = free lunch?

Autoregressive next token prediction and KV Cache in transformers

Understand the optimization technique in LLMs to speed up token generation…