brainstate

Tiiny-AI/PowerInfer

High-speed Large Language Model Serving for Local Deployment

C++★ 9.9kMITGitHub ↗

History and source changes · Reports and owner responses · Compare

Similar

  1. Lightning-AI/litgpt

    20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

    Python★ 13.7kApache-2.0GitHub ↗

    Why this match

    topics large-language-models, llm, llm-inference; language differs: C++ → Python; license differs: MIT → Apache-2.0

  2. cocktailpeanut/dalai

    The simplest way to run LLaMA on your local machine

    CSS★ 12.9kGitHub ↗

    Why this match

    topics llama, llm; language differs: C++ → CSS

  3. 01-ai/Yi

    A series of large language models trained from scratch by developers @01-ai

    Jupyter Notebook★ 7.8kApache-2.0GitHub ↗

    Why this match

    topics large-language-models; language differs: C++ → Jupyter Notebook; license differs: MIT → Apache-2.0

  4. mistralai/mistral-inference

    Official inference library for Mistral models

    Jupyter Notebook★ 10.8kApache-2.0archivedGitHub ↗

    Why this match

    topics llm, llm-inference; language differs: C++ → Jupyter Notebook; license differs: MIT → Apache-2.0

  5. GreyDGL/PentestGPT

    Automated Penetration Testing Agentic Framework Powered by Large Language Models

    Python★ 16.3kMITGitHub ↗

    Why this match

    topics large-language-models, llm; language differs: C++ → Python

  6. arcee-ai/mergekit

    Tools for merging pretrained large language models.

    Python★ 7.4kLGPL-3.0GitHub ↗

    Why this match

    topics llama, llm; language differs: C++ → Python; license differs: MIT → LGPL-3.0

  7. eugeneyan/open-llms

    📋 A list of open LLMs available for commercial use.

    ★ 12.9kApache-2.0GitHub ↗

    Why this match

    topics large-language-models, llm; license differs: MIT → Apache-2.0

  8. liguodongiot/llm-action

    本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)

    HTML★ 25.2kApache-2.0GitHub ↗

    Why this match

    topics llm, llm-inference; language differs: C++ → HTML; license differs: MIT → Apache-2.0