geohot / dumbrlLinks
Can RL solve simple problems?
☆54Updated last year
Alternatives and similar repositories for dumbrl
Users that are interested in dumbrl are comparing it to the libraries listed below
Sorting:
- An implementation of delta-iris in tinygrad☆72Updated 9 months ago
- Scripts and environment for the tinybox☆93Updated last year
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated last year
- This repository contain the simple llama3 implementation in pure jax.☆64Updated 3 months ago
- Because it's there.☆16Updated 8 months ago
- Tensor library with autograd using only Rust's standard library☆68Updated 11 months ago
- Extensive introductory writeup on Zig language functionalities☆10Updated 10 months ago
- ☆27Updated 10 months ago
- ☆38Updated last week
- in this repository, i'm going to implement increasingly complex llm inference optimizations☆58Updated 2 weeks ago
- SIMD quantization kernels☆70Updated this week
- Noob Lessons from Stream about how GPUs work☆117Updated last month
- A really tiny autograd engine☆94Updated last week
- Rust Implementation of micrograd☆51Updated 11 months ago
- comma body does a loop around the office☆26Updated last year
- ☆130Updated 7 months ago
- Solve puzzles. Learn CUDA.☆64Updated last year
- ctypes wrappers for HIP, CUDA, and OpenCL☆129Updated 11 months ago
- Training AI for Super Smash Bros. Melee☆27Updated 2 months ago
- LLM training in simple, raw C/Metal Shading Language☆54Updated last year
- A synthetic story narration dataset to study small audio LMs.☆31Updated last year
- compute, storage, and networking infra at home☆64Updated last year
- Exploration into the Firefly algorithm in Pytorch☆39Updated 3 months ago
- Write a fast kernel and run it on Discord. See how you compare against the best!☆44Updated this week
- ☆60Updated last year
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆59Updated last year
- a highly efficient compression algorithm for the n1 implant (neuralink's compression challenge)☆46Updated last year
- Efficient baselines for autocurricula in JAX.☆187Updated 9 months ago
- Semantic search over every Emergent Ventures winner.☆23Updated 3 weeks ago
- could we make an ml stack in 100,000 lines of code?☆42Updated 10 months ago