The paper presents a memory layer called galahad-kv that stores the key-value state of a large language model’s context blocks (≈16,000 tokens each) on encrypted local NVMe disk, allowing byte‑exact retrieval without recomputation. On a single NVIDIA H100, the authors tested the system with Gemma 4 12B and 31B models over 50 million tokens of real public text, achieving 100 % successful reloads, 2.8×–4.3× faster loading than recomputation, and 8.8×–12.3× lower GPU energy usage while keeping GPU memory flat. The models answered long‑range factual queries with high accuracy (82 % for 12B, 98 % for 31B) and did not hallucinate, demonstrating that stored state can extend effective context without expanding the attention window.
arXiv:2607. 27090v1 Announce Type: cross Abstract: Large language models are increasingly deployed with persistent personalized context, such as accumulated memory profiles or long conversation histories, that is shared across a user's many requests.
Large language models are increasingly deployed with persistent personalized context, such as accumulated memory profiles or long conversation histories, that is shared across a user's many requests. Production memory systems (e.
KVMem is a KV-context virtualization system that allows large language model agents to maintain workspaces exceeding both GPU key‑value capacity and the model’s native context window. It stores overflowed history as paged KV state across GPU memory, host memory, and NVMe, using lightweight, model‑native attention‑space indexes to retrieve relevant historical blocks. Evaluations on long‑context agent benchmarks show that KVMem improves task utility and inference efficiency, enabling up to one million‑token workspaces on consumer GPUs and achieving interactive responsiveness in local deployments.
A transformer language model performs a bounded amount of computation per token, and recent work by Vishal Sikka, former CEO of Infosys, argues that this bound limits which tasks a model can carry out...
The paper introduces Galahad, a memory layer that stores a transformer language model’s key‑value state for blocks of text, allowing subsequent requests to reuse previously computed attention rather than recomputing it. On seven real‑world datasets, 98.7% of prompt tokens were already read, and with Galahad the model could attend to an entire 97,000‑token corpus, achieving 98–100% recall on a 100‑fact test while reducing inference time and energy consumption dramatically. The approach was validated across 30 models and all runtimes, demonstrating that stateful inference can replace stateless serving without loss of accuracy.
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:2607. 14568v1 Announce Type: cross Abstract: A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.
arXiv:2610.28223v1 Announce Type: cross Abstract: Large language models can solve complex problems across a variety of subjects, such as mathematics and coding. For such complex analytical tasks, mod...
arXiv:2610.35529v1 Announce Type: cross Abstract: Interactive world models keep the KV of past chunks as retrieval memory so that revisited places stay consistent. On a single consumer machine (one R...
arXiv:2607. 19353v1 Announce Type: new Abstract: Confidential computing is becoming a practical deployment requirement for AI inference workloads that process sensitive inputs or protect proprietary model assets.
arXiv:2607. 15105v1 Announce Type: new Abstract: Parameter-efficient fine-tuning reduces model and optimizer memory, but dense attention still makes long training sequences expensive.
The paper introduces GraphTok, a GPU-based tokenizer that executes the entire tokenization pipeline as a single CUDA graph, matching reference token IDs for models such as GPT‑2, Llama 3, Qwen 2.5, DeepSeek‑V3, and Gemma 3. GraphTok achieves significant speedups, encoding one million GPT‑2 tokens in 1.7–3.2 ms and outperforming the leading CPU tokenizer gigatoken by 4.7–6.0× on Llama 3. In a vLLM deployment with cached prefixes, it reduces mean time‑to‑first‑token by 2.1–2.4× and dramatically increases request throughput, sustaining 518 req/s of 121k‑token traffic versus 296 with gigatoken.