🏊 Memory Pools - emschwartz · Scour

Mapping Gemma3 onto an Edge Dataflow Architecture

arxiv.org·1d

Evaluating and Enhancing the Vulnerability Reasoning Capabilities of Large Language Models

arxiv.org·1d

🏆LLM Benchmarking

Yet Another Blog Post About Programming With AI

amykhar.bearblog.dev·4d

👨‍💻AI Coding

tzcnt/TooManyCooks: C++20 concurrency framework with no compromises. Excellent performance, powerful features, and simple syntax.

github.com·1d

How we cut Vertex AI latency by 35% with GKE Inference Gateway

cloud.google.com·3d

🧠Inference Serving

MiquelNasarre/chaotic: Chaotic ― 3D renderer for your crazy math projects in C++. Minimal bloat, minimal complexity, maximal fun!

github.com·1d·

Discuss: Hacker News

✏️Code Editors

Private Data Space Model

privatedata.space·5d

📏Linear Types

The control layer for AI

blog.dottxt.ai·3d·

Discuss: Hacker News

🛡️AI Security

Anthropics Compiler Challenge

corsix.org·2d

🧮Compute Optimization

Scaling Smarter: Instant Nodes, Zero Wait

superorbital.io·4d

📅Resource Scheduling

Software Design by Example: A File Viewer

third-bit.com·3d

Sonic4Atari brings high-speed platform action to the Atari Lynx

generationamiga.com·2d

🪄Prompt Engineering

Same Surface, Different Weight

robpanico.com·3d·

Discuss: Hacker News

🤝Inclusive Design

OSTEP Chapters 6,7

muratbuffalo.blogspot.com·5d·

Discuss: Blogger

💾Persistence Strategies

Hardware Acceleration

jellyfin.org·2d

⚡Hardware Acceleration

How WebAssembly and Web Workers prevent UI freezes

thenewstack.io·3d

Continual learning and the post monolith AI era

baseten.co·3d·

Discuss: Hacker News

🧠LLM Inference

I Built a 6 BIPS JIT in Five Months

unlikelyemphasis.substack.com·4d·

Discuss: Substack

⚙️Language Runtimes

Virtual AI Memory Chips

pgsgrove.com·4d

AI Workflows with human-in-the-loop

weavemind.ai·2d·

Discuss: Hacker News

👨‍💻AI Coding

Loading more...