GitHub - kossisoroyce/timber: Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference.

Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x f...

Replacing Protobuf with Rust to go 5 times faster

CPU Cache-Friendly Data Structures in Go: 10x Speed with Same Algorithm

False sharing killed our performance. Data-oriented design saved it. Learn cache lines and NUMA.

Gimlet Blog

A blog about research on high performance AI systems.

HOLY SMOKES! A new, 200% faster DeepSeek R1-0528 variant appears from German lab TNG Technology Consulting GmbH

This gain is made possible by TNG’s Assembly-of-Experts (AoE) method — a technique for building LLMs by selectively merging the weight tensors

GitHub - kelindar/event: Simple internal event bus for Go applications

Simple internal event bus for Go applications. Contribute to kelindar/event development by creating an account on GitHub.

10,000 Times Faster, 10,000 Times Simpler: Why Today’s Solutions Don’t Need Internet-Scale Complexity

Securely connect to anything on the internet with Tailscale. Built on WireGuard®️, Tailscale enables you to make finely configurable connections, secured end-to-end according to zero trust principles, between any resources on any infrastructure.

krep - Blazing Fast String Search Utility