Motsepe-Jr / AI-research-papers-pseudo-codeLinks
This is a repo covers ai research papers pseudocodes
☆15Updated 2 years ago
Alternatives and similar repositories for AI-research-papers-pseudo-code
Users that are interested in AI-research-papers-pseudo-code are comparing it to the libraries listed below
Sorting:
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆95Updated 2 years ago
- a minimal cache manager for PagedAttention, on top of llama3.☆119Updated last year
- Easy and Efficient Quantization for Transformers☆203Updated 2 months ago
- ☆17Updated 2 years ago
- A minimal implementation of vllm.☆52Updated last year
- ring-attention experiments☆149Updated 10 months ago
- Explorations into some recent techniques surrounding speculative decoding☆283Updated 8 months ago
- Cataloging released Triton kernels.☆252Updated 7 months ago
- Applied AI experiments and examples for PyTorch☆292Updated last week
- ☆121Updated last year
- ☆234Updated last week
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆209Updated last week
- ☆214Updated 6 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆81Updated 11 months ago
- ☆26Updated last year
- ☆163Updated last year
- Mixed precision training from scratch with Tensors and CUDA☆25Updated last year
- This repository contains the experimental PyTorch native float8 training UX☆224Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆236Updated last week
- ☆118Updated last year
- Code for studying the super weight in LLM☆115Updated 8 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆144Updated last year
- Flash Attention in 300-500 lines of CUDA/C++☆24Updated last week
- NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day☆256Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆110Updated 3 months ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- ☆123Updated 3 months ago
- Prune transformer layers☆69Updated last year
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆262Updated last month
- Latency and Memory Analysis of Transformer Models for Training and Inference☆450Updated 4 months ago