CUDA Ray Tracing 2x Faster Than RTX: My CUDA Ray Tracing Journey
karimsayedre.github.io·2h·
Discuss: Hacker News
📊Performance Profiling
Floating-Point Data Transformation for Lossless Compression
arxiv.org·1d
🌊Streaming Compression
Portable Network Graphics (PNG) Specification (Third Edition)
w3.org·1d·
Discuss: Hacker News
🕸️WebP Analysis
🎬 Building a Text-to-Video Generator (Veo3.im): Lessons from Going from Blurry Prototypes to Usable 1080p Output
dev.to·2d·
Discuss: DEV
🎬AV1 Encoding
AMD researchers reduce graphics card VRAM capacity of 3D-rendered trees from 38GB to just 52 KB with work graphs and mesh nodes — shifting CPU work to the GPU y...
tomshardware.com·13h
🖥️Modern Terminals
Assembling the PC-6001
leadedsolder.com·1d
🎮GameBoy Architecture
Collaborative Texture Filtering
arxiv.org·1d
🎞️FFmpeg Filters
What Inflection AI Learned Porting Its LLM Inference Stack from NVIDIA to Intel Gaudi
thenewstack.io·5h
🧮Compute Optimization
Deep Dive into SVT-AV1's Evolution (Part 1)
wiki.x266.mov·5d·
Discuss: Lobsters, Hacker News
🎬AV1 Encoding
Enhancing AMD Radeon GPU Detective Output with DirectX Debug Information
gpuopen.com·1d·
Discuss: Hacker News
🛠️Greaseweazle
Show HN: Anagnorisis, local data-management with trainable recommendation engine
github.com·36m·
Discuss: Hacker News
🤖Archive Automation
SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation
arxiv.org·1d
⚡Modern Compression
82 x 50mm SoM combines NXP i.MX 8M Mini SoC with 25 TOPS DEEPX DX-M1 AI accelerator
cnx-software.com·6h
🖥️Hardware Architecture
UltraSketchLLM: Saliency-Driven Sketching for Ultra-Low Bit LLM Compression
arxiv.org·1d
🗜️LZW Variants
See the Bigger Picture: Image Feature Engineering for Search & Recs
shaped.ai·2d
📊Learned Metrics
Modeling the World in 280 Characters
tympanus.net·2d·
Discuss: Lobsters, Hacker News
⟷Bidirectional Programming
From Zero to One: A Complete Guide to Implementing WeChat Sharing in HarmonyOS
dev.to·15h·
Discuss: DEV
⚡Modern Compression
Meet Mojo: The Language That Could Replace Python, C++, and CUDA
hackernoon.com·16h
⬆️Lambda Lifting
Video Compression for Spatiotemporal Earth System Data
arxiv.org·19h
📊Rate-Distortion Theory
davidchisnall/igk: I got Knuth'd: A compiler for documents
github.com·17h
📝Concrete Syntax