ridgerchu / matmulfreellm
Implementation for MatMul-free LM.
☆2,986Updated 5 months ago
Alternatives and similar repositories for matmulfreellm:
Users that are interested in matmulfreellm are comparing it to the libraries listed below
- Efficient Triton Kernels for LLM Training☆4,873Updated this week
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,758Updated 2 weeks ago
- Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch☆1,795Updated 2 weeks ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆862Updated 2 months ago
- Tile primitives for speedy kernels☆2,279Updated this week
- NanoGPT (124M) in 3 minutes☆2,493Updated 3 weeks ago
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,567Updated this week
- A modern model graph visualizer and debugger☆1,167Updated this week
- PyTorch native post-training library☆5,103Updated this week
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,288Updated this week
- Tools for merging pretrained large language models.☆5,571Updated this week
- nanoGPT style version of Llama 3.1☆1,356Updated 8 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆3,355Updated 5 months ago
- llama3.np is a pure NumPy implementation for Llama 3 model.☆981Updated 10 months ago
- A PyTorch native library for large-scale model training☆3,607Updated this week
- Schedule-Free Optimization in PyTorch☆2,142Updated last week
- ☆4,077Updated 10 months ago
- Distributed Training Over-The-Internet☆901Updated 4 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆628Updated 3 weeks ago
- A simple, performant and scalable Jax LLM!☆1,690Updated this week
- Thunder gives you PyTorch models superpowers for training and inference. Unlock out-of-the-box optimizations for performance, memory and …☆1,325Updated this week
- Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.☆2,028Updated this week
- Puzzles for learning Triton☆1,577Updated 5 months ago
- Inference Llama 2 in one file of pure 🔥☆2,110Updated 11 months ago
- Blazingly fast LLM inference.☆5,437Updated this week
- 4M: Massively Multimodal Masked Modeling☆1,714Updated last month
- A nanoGPT pipeline packed in a spreadsheet☆2,110Updated 10 months ago
- Modeling, training, eval, and inference code for OLMo☆5,502Updated this week
- Examples in the MLX framework☆7,306Updated 3 weeks ago
- Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.☆1,984Updated 8 months ago