pytorch-labs / gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
☆5,892Updated last week
Alternatives and similar repositories for gpt-fast:
Users that are interested in gpt-fast are comparing it to the libraries listed below
- Accessible large language models via k-bit quantization for PyTorch.☆6,818Updated this week
- PyTorch native post-training library☆5,014Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,830Updated 8 months ago
- Fast and memory-efficient exact attention☆16,370Updated last week
- A PyTorch native library for large model training☆3,470Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,861Updated this week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,466Updated 8 months ago
- Robust recipes to align language models with human and AI preferences☆5,072Updated 4 months ago
- Tools for merging pretrained large language models.☆5,458Updated this week
- A framework for few-shot evaluation of language models.☆8,337Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,161Updated 5 months ago
- Train transformer language models with reinforcement learning.☆12,591Updated this week
- TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain…☆9,762Updated this week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,043Updated 6 months ago
- ☆4,069Updated 9 months ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,766Updated this week
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,523Updated 4 months ago
- The official PyTorch implementation of Google's Gemma models☆5,397Updated this week
- Modeling, training, eval, and inference code for OLMo☆5,401Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,990Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,042Updated this week
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆9,502Updated 8 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆12,220Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,324Updated 10 months ago
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,423Updated last week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆11,841Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,216Updated 2 weeks ago
- Large Language Model Text Generation Inference☆9,905Updated this week
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,832Updated last year
- Go ahead and axolotl questions☆8,882Updated this week