davidar / eigenGPTLinks
Minimal C++ implementation of GPT2
☆40Updated 2 years ago
Alternatives and similar repositories for eigenGPT
Users that are interested in eigenGPT are comparing it to the libraries listed below
Sorting:
- throwaway GPT inference☆140Updated last year
- Inference Llama 2 in one file of pure C++☆83Updated 2 years ago
- RWKV in nanoGPT style☆193Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Updated 11 months ago
- Exploration into the Firefly algorithm in Pytorch☆40Updated 7 months ago
- Lightweight Llama 3 8B Inference Engine in CUDA C☆49Updated 6 months ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- Inference of Mamba models in pure C☆191Updated last year
- MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection☆46Updated 2 years ago
- ☆32Updated last year
- ☆53Updated last year
- OMNI: Open-endedness via Models of human Notions of Interestingness☆56Updated 7 months ago
- Fast and memory efficient PyTorch implementation of the Perceiver with FlashAttention.☆29Updated 10 months ago
- Token Omission Via Attention☆128Updated 11 months ago
- Efficiently send large arrays across machines☆16Updated last year
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆46Updated last year
- Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.☆73Updated 7 months ago
- Multi-Layer Key-Value sharing experiments on Pythia models☆34Updated last year
- Make triton easier☆47Updated last year
- A really tiny autograd engine☆94Updated 3 months ago
- ☆19Updated 2 years ago
- ☆46Updated 2 months ago
- A thin, highly portable toolkit for efficiently compiling dense loop-based computation.☆148Updated 2 years ago
- ☆60Updated 8 months ago
- [ICML 2023] "Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation", Wenqing Zheng, S P Sharan, Ajay Kumar Jaiswal, …☆41Updated last year
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆108Updated 11 months ago
- Memoria is a human-inspired memory architecture for neural networks.☆75Updated 11 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 3 months ago
- ☆28Updated last year
- ☆89Updated last year