Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
☆6,184Aug 22, 2025Updated 6 months ago
Alternatives and similar repositories for gpt-fast
Users that are interested in gpt-fast are comparing it to the libraries listed below
Sorting:
- A PyTorch native platform for training generative AI models☆5,098Updated this week
- Fast and memory-efficient exact attention☆22,460Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆7,997Feb 26, 2026Updated last week
- PyTorch native post-training library☆5,691Feb 27, 2026Updated last week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆23,905Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆13,206Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆12,993Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,196Jul 11, 2024Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆71,883Updated this week
- Development repository for the Triton language and compiler☆18,501Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,707Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,896May 3, 2024Updated last year
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,356Feb 20, 2026Updated 2 weeks ago
- Minimalistic large language model 3D-parallelism training☆2,579Feb 19, 2026Updated 2 weeks ago
- Large Language Model Text Generation Inference☆10,788Jan 8, 2026Updated last month
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,710Jun 25, 2024Updated last year
- Efficient Triton Kernels for LLM Training☆6,162Feb 27, 2026Updated last week
- Train transformer language models with reinforcement learning.☆17,523Updated this week
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,347Jul 1, 2024Updated last year
- Robust recipes to align language models with human and AI preferences☆5,510Sep 8, 2025Updated 5 months ago
- Inference Llama 2 in one file of pure C☆19,213Aug 6, 2024Updated last year
- High-speed Large Language Model Serving for Local Deployment☆8,756Jan 24, 2026Updated last month
- Transformer related optimization, including BERT, GPT☆6,398Mar 27, 2024Updated last year
- Official inference library for Mistral models☆10,690Feb 26, 2026Updated last week
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,843Jun 10, 2024Updated last year
- Ongoing research training transformer models at scale☆15,461Updated this week
- Tile primitives for speedy kernels☆3,202Feb 24, 2026Updated last week
- FlashInfer: Kernel Library for LLM Serving☆5,057Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,919Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,443Jul 17, 2025Updated 7 months ago
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆41,706Feb 27, 2026Updated last week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆54,071Nov 12, 2025Updated 3 months ago
- Tools for merging pretrained large language models.☆6,826Updated this week
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆24,500Aug 12, 2024Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,315Mar 6, 2025Updated last year
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆20,717Updated this week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,082Jul 1, 2025Updated 8 months ago
- LLM training in simple, raw C/CUDA☆28,993Jun 26, 2025Updated 8 months ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆5,027Apr 11, 2025Updated 10 months ago