Alternatives and similar repositories for gpt-fast

Users that are interested in gpt-fast are comparing it to the libraries listed below

• pytorch / torchtune
  PyTorch native post-training library
  ☆5,493Updated this week
• pytorch / torchtitan
  A PyTorch native platform for training generative AI models
  ☆4,395Updated this week
• allenai / OLMo
  Modeling, training, eval, and inference code for OLMo
  ☆5,985Updated 2 weeks ago
• huggingface / alignment-handbook
  Robust recipes to align language models with human and AI preferences
  ☆5,373Updated 2 weeks ago
• jzhang38 / TinyLlama
  The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
  ☆8,750Updated last year
• mit-han-lab / streaming-llm
  [ICLR 2024] Efficient Streaming Language Models with Attention Sinks
  ☆7,046Updated last year
• mit-han-lab / llm-awq
  [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
  ☆3,258Updated 2 months ago
• AnswerDotAI / fsdp_qlora
  Training LLMs with QLoRA + FSDP
  ☆1,528Updated 10 months ago
• bitsandbytes-foundation / bitsandbytes
  Accessible large language models via k-bit quantization for PyTorch.
  ☆7,584Updated last week
• openai / transformer-debugger
  ☆4,094Updated last year
• arcee-ai / mergekit
  Tools for merging pretrained large language models.
  ☆6,297Updated this week
• jiaweizzhao / GaLore
  GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
  ☆1,606Updated 10 months ago
• intel / intel-extension-for-transformers
  ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…
  ☆2,170Updated 11 months ago
• FasterDecoding / Medusa
  Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
  ☆2,623Updated last year
• casper-hansen / AutoAWQ
  AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
  ☆2,249Updated 4 months ago
• KellerJordan / modded-nanogpt
  NanoGPT (124M) in 3 minutes
  ☆3,126Updated 2 months ago
• dvmazur / mixtral-offloading
  Run Mixtral-8x7B models in Colab or consumer desktops
  ☆2,323Updated last year
• EleutherAI / lm-evaluation-harness
  A framework for few-shot evaluation of language models.
  ☆10,161Updated last week
• huggingface / nanotron
  Minimalistic large language model 3D-parallelism training
  ☆2,212Updated 2 weeks ago
• karpathy / minbpe
  Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
  ☆9,936Updated last year
• NVIDIA / TensorRT-LLM
  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizati…
  ☆11,625Updated this week
• google / gemma_pytorch
  The official PyTorch implementation of Google's Gemma models
  ☆5,548Updated 3 months ago
• SJTU-IPADS / PowerInfer
  High-speed Large Language Model Serving for Local Deployment
  ☆8,334Updated last month
• ModelTC / LightLLM
  LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…
  ☆3,605Updated this week
• HazyResearch / ThunderKittens
  Tile primitives for speedy kernels
  ☆2,704Updated last week
• srush / Triton-Puzzles
  Puzzles for learning Triton
  ☆1,992Updated 10 months ago
• karpathy / nano-llama31
  nanoGPT style version of Llama 3.1
  ☆1,423Updated last year
• AutoGPTQ / AutoGPTQ
  An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
  ☆4,948Updated 5 months ago
• lucidrains / self-rewarding-lm-pytorch
  Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
  ☆1,402Updated last year
• huggingface / optimum-nvidia
  ☆1,002Updated 7 months ago