✂️ Prefill Disaggregation - teslartifex · Scour

(PR) Agentic AI Drives Structural Expansion in Memory Demand, Global Memory Market Projected to Reach US$1.28 Trillion by 2027 🚀Performance

techpowerup.com·14h

The surprising depths of prompt caching 💾Cache Optimization

opub.dev·3d·Hacker News

RTP-LLM: High-Performance Alibaba LLM Inference Engine 🤖LLM Inference

Local LLM Deployment: Ollama vs vLLM vs LM Studio Compared 🤖LLM Inference

sitepoint.com·1d

jmaczan/tiny-vllm: Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM 🤖LLM Inference

github.com·32m·Hacker News

The Shape Of Prompts: Exploring Their Effect On Inference Infrastructure 🚀Performance

semiengineering.com·1d

Inference Scaling for Large Language Models: Micron and Argonne Study on Reasoning Workloads - News and Statistics 🤖LLM Inference

indexbox.io·3d

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 Par... 🚀Performance

techmeme.com·7h

Nvidia Dynamo Snapshot: Fast Startup for Inference Workloads on Kubernetes 🚀Performance

developer.nvidia.com·1d·Hacker News

Tokenization Is the Bottleneck You’re Not Measuring ⏱️Latency Engineering

ranvier.systems·4d·Hacker News

Reachy Mini goes fully local ⏱️Latency Engineering

huggingface.co·23h·Hacker News

The LLM Inference Optimization: Quantization to Speculative Decoding Part 2 🤖LLM Inference

digitalocean.com·2d

Silicon Motion Introduces SM2524XT PCIe Gen5 DRAM-less SSD Controller 💾NVMe

storagereview.com·1h

Less-relevant results

Startup XCENA hits $570M valuation after Series B funding round 🪟Tauri

cryptobriefing.com·7h

Multi-Query Attention ⚡Flash Attention

·4d

The Anatomy of an LLM | Interactive Visual Guide to How Language Models Work 🧠LLMs

royvanrijn.com·1d·Hacker News

LongLive 2.0: NVFP4 is intended to make long AI videos faster and more memory-efficient 🤖LLM Inference

igorslab.de·3d

Awesome List Updated on May 28, 2026 ⚡Tokio

trackawesomelist.com·1d

I tested 3 tiny local LLMs for everyday work, and only one of them impressed me 🤖LLM Inference

xda-developers.com·6d

Mistral AI chooses VAST Data for its AI data foundation 📡Edge AI

blocksandfiles.com·4h

Log in to enable infinite scrolling