Qubitium

Qubitium's Stars

• Aider-AI/aider

  aider is AI pair programming in your terminal

  Language:Python25k1622.5k2.3k

• allegroai/clearml

  ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

  Language:Python5.8k971.1k660

• microsoft/TinyTroupe

  LLM-powered multiagent persona simulation for imagination enhancement and business insights.

  Language:Python5.3k5129424

• intel/intel-extension-for-pytorch

  A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

  Language:Python1.7k40586258

• evalplus/evalplus

  Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

  Language:Python1.3k9192117

• ashvardanian/SimSIMD

  Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, and bit vectors using SIMD for both AVX2, AVX-512, NEON, SVE, & SVE2 📐

  Language:C1.2k209768

• trotsky1997/MathBlackBox

  Language:Python9962610101

• mit-han-lab/nunchaku

  SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

  Language:Cuda586127432

• makeecat/Peng

  A minimal quadrotor autonomy framework in Rust (Mac, Linux, Windows)

  Language:Rust58215523

• AGI-Arena/MARS

  The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models

  Language:Python45136167

• spcl/QuaRot

  Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.

  Language:Python317115527

• bigcode-project/bigcodebench

  BigCodeBench: Benchmarking Code Generation Towards AGI

  Language:Python27264730

• KellerJordan/Muon

  Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead

  Language:Python210456

• ModelCloud/GPTQModel

  Production ready LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.

  Language:Python20338931

• haonan3/AnchorContext

  AnchorAttention: Improved attention for LLMs long-context training

  Language:Python202306

• THUDM/Android-Lab

  Language:Python18112129

• bloc97/DeMo

  DeMo: Decoupled Momentum Optimization

  Language:Python170207

• Jellyfish042/Sudoku-RWKV

  Language:Python111515

• xdit-project/mochi-xdit

  faster parallel inference of mochi-1 video generation model

  Language:Python1077

• amd/ZenDNN

  Language:C++999914

• huggingface/optimum-graphcore

  Blazing fast training of 🤗 Transformers on Graphcore IPUs

  Language:Python84444735

• ModelTC/Outlier_Suppression_Plus

  Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

  Language:Python45963

• gorse-io/goat

  Go assembly transpiler for C programming language

  Language:Go44473

• gonglinyuan/safim

  Language:Python27231

• MooreThreads/mutlass

  MUSA Templates for Linear Algebra Subroutines

  Language:C++18103

• graphcore/Gradient-HuggingFace

  Tasks and tutorials using Graphore's IPU with Hugging Face. Originally at https://github.com/gradient-ai/Graphcore-HuggingFace

  Language:Jupyter Notebook12517

• ModelCloud/Device-SMI

  Self-contained Python lib with zero-dependencies that give you a unified device properties for gpu, cpu, and npu. No more calling separate tools such as nvidia-smi or /proc/cpuinfo and parsing it yourself.

  Language:Python9171

• IST-DASLab/ISTA-DASLab-Optimizers

  Language:Python7520

• waefrebeorn/GradRetentionNet

  GradRetentionNet: A Research Project Exploring Persistent Gradient Descent for Improved Global Optimization

  Language:Python70

• NonvolatileMemory/fast_llm_sampling

  fast sampling from categorical distribution

  Language:Python2