a1k0n / a1gpt
throwaway GPT inference
☆139Updated 3 months ago
Related projects: ⓘ
- ☆230Updated 5 months ago
- Fast multi-threaded matrix multiplication in C☆164Updated 3 weeks ago
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆249Updated 9 months ago
- Deep learning accelerator architectures requiring half the multipliers☆259Updated 5 months ago
- Richard is gaining power☆171Updated last month
- An implementation of bucketMul LLM inference☆212Updated 2 months ago
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆190Updated 3 months ago
- A BERT that you can train on a (gaming) laptop.☆212Updated last year
- ☆249Updated last year
- Exploring the scalable matrix extension of the Apple M4 processor☆91Updated 3 months ago
- a small code base for training large models☆261Updated this week
- Inference of Mamba models in pure C☆176Updated 6 months ago
- GGUF implementation in C as a library and a tools CLI program☆238Updated 2 months ago
- Hashed Lookup Table based Matrix Multiplication (halutmatmul) - Stella Nera accelerator☆205Updated 9 months ago
- DiscoGrad - automatically differentiate across conditional branches in C++ programs☆202Updated last week
- Wang Yi's GPT solution☆137Updated 9 months ago
- ☆162Updated 3 months ago
- Visualize the intermediate output of Mistral 7B☆300Updated 7 months ago
- WebGPU LLM inference tuned by hand☆145Updated last year
- Autograd to GPT-2 completely from scratch☆104Updated last month
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆269Updated last month
- A Detailed Introduction to My Favorite Statistical Measure, Hoeffding's D☆94Updated 6 months ago
- A pure NumPy implementation of Mamba.☆212Updated 2 months ago
- A really tiny autograd engine☆85Updated 5 months ago
- Tiny Dream - An embedded, Header Only, Stable Diffusion C++ implementation☆248Updated 10 months ago
- Mistral7B playing DOOM☆117Updated 2 months ago
- Tiny inference-only implementation of LLaMA☆91Updated 5 months ago
- The Fast Vector Similarity Library is designed to provide efficient computation of various similarity measures between vectors.☆344Updated this week
- C++ raytracer that supports custom models. Supports running the calculations on the CPU using C++11 threads or in the GPU via CUDA.☆74Updated last year
- ☆283Updated 5 months ago