leemgs

Geunsik Lim's starred repositories

neovim

Vim-fork focused on extensibility and usability

Language:Vim ScriptNOASSERTION81060 984 11573

fastapi

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Language:PythonMIT73959 674 3417

llama.cpp

LLM inference in C/C++

Language:C++MIT63917 534 3619

chakra-ui

⚡️ Simple, Modular & Accessible UI Components for your React Applications

Language:MDXMIT37337 207 3634

llama_index

LlamaIndex is a data framework for your LLM applications

Language:PythonMIT34629 247 4862

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Language:PythonApache-2.032741 475 18247

OpenDevin

🐚 OpenDevin: Code Less, Make More

Language:PythonMIT30189 281 1252

jq

Command-line JSON processor

Language:CNOASSERTION29943 326 2200

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Language:PythonApache-2.013052 98 1039

liquid

Liquid markup language. Safe, customer facing template language for flexible web apps.

Language:RubyMIT10980 771 866

ggml

Tensor library for machine learning

Language:C++MIT10660 123 393

peek

Simple animated GIF screen recorder with an easy to use interface

Language:ValaGPL-3.010206 74 1210

FlexGen

Running large language models on a single GPU for throughput-oriented scenarios.

Language:PythonApache-2.09108 110 81

ZLUDA

CUDA on ??? GPUs

Language:RustApache-2.08821 126 159

ml-ferret

Language:PythonNOASSERTION8270 1570

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Language:C++MIT7794 76 154

skypilot

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

Language:PythonApache-2.06419 71 1669