Stars
[ECCV 2022] TinyViT: Fast Pretraining Distillation for Small Vision Transformers (https://github.com/microsoft/Cream/tree/main/TinyViT)
LM engine is a library for pretraining/finetuning LLMs
jcvtieck / OpenMythos
Forked from kyegomez/OpenMythosA theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
Official inference framework for 1-bit LLMs
50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.
Development repository for the Triton language and compiler
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Official implementation of our paper "Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models"
A State-Space Model with Rational Transfer Function Representation.
A massively parallel, high-level programming language
Sparsity-aware deep learning inference runtime for CPUs
Code for our NeurIPS 2021 paper: Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains
Open weights language model from Google DeepMind, based on Griffin.
jaxsnn is an event-based approach to machine-learning-inspired training and simulation of SNNs, including support for the BrainScaleS-2 neuromorphic backend.
Zulip-Notion linking bot that saves arxiv papers and their info when their link is posted in Zulip
Some preliminary explorations of Mamba's context scaling.
A highly experimental vi-inspired editor where you edit code, not text.