misa77: A new LZ-based compression codec achieving 1.5-3x faster decompression than LZ4 on x86 and ARM

Next-Level Inference: Why Your Single-Node vLLM Setup Needs Prefill-Decode Disaggregation

How single-node prefill/decode disaggregation in vLLM uses AMD MORI-IO on an 8-GPU MI300X node to separate prefill and decode, transfer KV c

Achieving Up to 67% Cost Savings with Prefill-Decode Disaggregation Using Ray + vLLM on AMD MI325X

Xiaomi MiMo Team Details Full-Pipeline Inference Optimization for Hybrid SWA + MoE Multimodal LLM Serving

We present a full-pipeline inference optimization for the MiMo-V2.5 model family, which combines Hybrid Sliding Window Attention (Hybrid SWA

CVE-2026-61455: Improper Handling of Highly Compressed Data (Data Amplification) in getgrav grav

Grav versions before 2.0.1 have a decompression bomb vulnerability in the ZipArchiver::extract() function. This vulnerability arises because

RTP-LLM: Alibaba's High-Performance Inference Engine for Large Language Model Deployment

Large Language Models (LLMs) have revolutionized AI applications, but deploying them at scale presents significant challenges. We present RT

TinyFast: Local File Compression Tool for macOS

TinyFast is a macOS app that compresses PNG, JPEG, MP4, MOV, PDF, and GIF files locally. Just drag and drop your file in and out. It’s fast,