Lists (1)
Sort Name ascending (A-Z)
Stars
Self-hosted SSH and remote desktop management.
Research into AI engineering interview assignments, take-home challenges, and hiring practices from 2026
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
DeepGEMM: clean and efficient BLAS kernel library on GPU
Code space for different neural networks in pytorch
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Notes on the Mamba and the S4 model (Mamba: Linear-Time Sequence Modeling with Selective State Spaces)
TRACER: replace 90%+ of your LLM classification calls with a traditional ML model. Formal parity guarantees. Self-improving.
Your agent's favorite harness, built on Pydantic AI
A minimal, secure Python interpreter written in Rust for use by AI
Lightweight coding agent that runs in your terminal
SGLang is a high-performance serving framework for large language models and multimodal models.
browser renderer & emulator for post-training domdiff rewards.
Causal depthwise conv1d in CUDA, with a PyTorch interface
Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting.
Join Discord: https://discord.gg/5TUQKqFWd / claw-code Rust port parity work - it is temporary work while claw-code repo is doing migration
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Train the smallest LM you can that fits in 16MB. Best model wins!
andyluo7 / autoresearch
Forked from karpathy/autoresearchAI agents running research on single-GPU nanochat training automatically
AI agents running research on single-GPU nanochat training automatically
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物
🙌 OpenHands: AI-Driven Development
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr...
Train transformer language models with reinforcement learning.
Can AdamW written in Triton be as performant as fused CUDA impl?