Beast code in Giters

Mxiim's starred repositories

llama.cpp

LLM inference in C/C++

Language:C++MIT5911600

llama-cpp-python

Python bindings for llama.cpp

Language:PythonMIT680000

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Language:PythonNOASSERTION1413100

awesome-ml-serving

A curated list of awesome open source and commercial platforms for serving models in production 🚀

Apache-2.01900

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Language:Jupyter NotebookApache-2.0192500

deepeval

The LLM Evaluation Framework

Language:PythonApache-2.0200000

fsdp_qlora

Training LLMs with QLoRA + FSDP

Language:Jupyter NotebookApache-2.0125300

py-spy

Sampling profiler for Python programs

Language:RustMIT1198200

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Language:PythonApache-2.012677600

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Language:PythonApache-2.02013700

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

Language:PythonApache-2.0512500

gpustat

📊 A simple command-line utility for querying and monitoring GPU status

Language:PythonMIT389000

nvtop

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

Language:CNOASSERTION753700

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Language:PythonApache-2.01060500

inference

Reference implementations of MLPerf™ inference benchmarks

Language:PythonApache-2.0110600

vim-visual-multi

Multiple cursors plugin for vim/neovim

Language:Vim ScriptMIT387500

wish

Make SSH apps, just like that! 💫

Language:GoMIT313200

bubbletea

A powerful little TUI framework 🏗

Language:GoMIT2477000

SketchyBar

A highly customizable macOS status bar replacement

Language:CGPL-3.0482600

AeroSpace

AeroSpace is an i3-like tiling window manager for macOS

Language:SwiftMIT148200

napkin-math

Techniques and numbers for estimating system's performance from first-principles

Language:RustMIT312700

microvm.nix

NixOS MicroVMs

Language:NixMIT106800

Metal

Metal examples using C++

Language:C++MIT1500

UTM

Virtual machines for iOS and macOS

Language:SwiftApache-2.02462300

delve

Delve is a debugger for the Go programming language.

Language:GoMIT2219600

firejail

Linux namespaces and seccomp-bpf sandbox

Language:CGPL-2.0548900

go_profiling_talk

Code used in the "Go Profiling and Optimization" talk

Language:Go7000

kubernetes-the-hard-way

Bootstrap Kubernetes the hard way. No scripts.

Apache-2.03928800

papers-we-love

Papers from the computer science community to read and discuss.

Language:Shell8429000

dragonfly

A modern replacement for Redis and Memcached

Language:C++NOASSERTION2415000