mlecauchois / micrograd-cudaLinks
☆243Updated last year
Alternatives and similar repositories for micrograd-cuda
Users that are interested in micrograd-cuda are comparing it to the libraries listed below
Sorting:
- Pytorch script hot swap: Change code without unloading your LLM from VRAM☆126Updated last month
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆251Updated last year
- DiscoGrad - automatically differentiate across conditional branches in C++ programs☆202Updated 8 months ago
- Algebraic enhancements for GEMM & AI accelerators☆277Updated 3 months ago
- A BERT that you can train on a (gaming) laptop.☆207Updated last year
- throwaway GPT inference☆139Updated last year
- R.L. methods and techniques.☆191Updated 6 months ago
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆205Updated 6 months ago
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆615Updated 2 months ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆367Updated 11 months ago
- Richard is gaining power☆187Updated 6 months ago
- A pure NumPy implementation of Mamba.☆223Updated 10 months ago
- Solve puzzles. Learn CUDA.☆64Updated last year
- An implementation of bucketMul LLM inference☆217Updated 11 months ago
- ☆228Updated this week
- Multi-Threaded FP32 Matrix Multiplication on x86 CPUs☆351Updated last month
- Heirarchical Navigable Small Worlds☆96Updated last month
- ☆47Updated 2 months ago
- a small code base for training large models☆300Updated last month
- GGUF implementation in C as a library and a tools CLI program☆270Updated 4 months ago
- Autograd to GPT-2 completely from scratch☆113Updated last month
- Visualize the intermediate output of Mistral 7B☆363Updated 4 months ago
- Machine Learning with Symbolic Tensors☆278Updated last week
- Designing bridge trusses with Pytorch autograd☆61Updated last year
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆285Updated this week
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.☆419Updated last month
- Docker-based inference engine for AMD GPUs☆230Updated 7 months ago
- ☆192Updated last month
- Open weights language model from Google DeepMind, based on Griffin.☆639Updated 2 weeks ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆833Updated 5 months ago