pytorch-labs / gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
☆5,749Updated last month
Alternatives and similar repositories for gpt-fast:
Users that are interested in gpt-fast are comparing it to the libraries listed below
- PyTorch native post-training library☆4,703Updated this week
- A PyTorch native library for large model training☆3,091Updated this week
- Tools for merging pretrained large language models.☆5,113Updated last week
- ☆4,050Updated 7 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆7,353Updated this week
- Robust recipes to align language models with human and AI preferences☆4,896Updated last month
- Modeling, training, eval, and inference code for OLMo☆5,024Updated this week
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,481Updated 2 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆6,522Updated this week
- Training LLMs with QLoRA + FSDP☆1,436Updated 2 months ago
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆11,197Updated this week
- Go ahead and axolotl questions☆8,293Updated this week
- A framework for few-shot evaluation of language models.☆7,474Updated this week
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆9,326Updated 6 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,669Updated last week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,749Updated 6 months ago
- The official PyTorch implementation of Google's Gemma models☆5,338Updated last week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,371Updated 6 months ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,620Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,113Updated 8 months ago
- TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain…☆9,147Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,152Updated 3 months ago
- Efficient Triton Kernels for LLM Training☆4,183Updated this week
- NanoGPT (124M) in 3.4 minutes☆2,068Updated last week
- Train transformer language models with reinforcement learning.☆10,609Updated this week
- Reaching LLaMA2 Performance with 0.1M Dollars☆965Updated 5 months ago
- PyTorch code and models for V-JEPA self-supervised learning from video.☆2,745Updated 5 months ago
- Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors a…☆1,257Updated this week
- ☆2,289Updated this week
- PyTorch native quantization and sparsity for training and inference☆1,753Updated this week