Skip to content

@IST-DASLab IST Austria Distributed Algorithms and Systems Lab

Change the repository type filter

All

    Repositories list

    85 repositories

    • SLQ

      Public
      Official implementation for "Statistically-Lossless Quantization of Large Language Models"
      0•0•0•0•Updated May 4, 2026May 4, 2026

    • Quartet-II

      Public
      Quartet II Official Code
      pytorchquantizationqat
      pytorchquantizationqatllm
      Python
      •8•70•0•1•Updated May 1, 2026May 1, 2026

    • WUSH

      Public
      Official Repository for "WUSH: Near-Optimal Adaptive Transforms for LLM Quantization"
      Python
      •
      Apache License 2.0
      •0•5•0•0•Updated Apr 27, 2026Apr 27, 2026

    • CloverLM

      Public
      🍀 Codebase for CloverLM
      Python
      •
      MIT License
      •0•7•0•1•Updated Apr 26, 2026Apr 26, 2026

    • Trion

      Public
      Code for Trion, a faster implementation of Dion (low-rank Muon) via Dynamic Column Selection based on a fixed projection matrix.
      0•0•0•0•Updated Apr 24, 2026Apr 24, 2026

    • GPTQ-Babai

      Public
      Official Repository for "The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm" (ICLR 2026)
      Python
      •
      MIT License
      •0•5•0•0•Updated Apr 16, 2026Apr 16, 2026

    • nanochat_optimizers

      Public
      The best ChatGPT that $100 can buy.
      Python
      •
      MIT License
      •7.1k•0•0•0•Updated Mar 27, 2026Mar 27, 2026

    • ISTA-DASLab-Optimizers

      Public
      Python
      •
      MIT License
      •0•14•0•0•Updated Mar 25, 2026Mar 25, 2026

    • Quartet

      Public
      Jupyter Notebook
      •
      MIT License
      •14•122•2•0•Updated Mar 18, 2026Mar 18, 2026

    • GridSearcher

      Public
      GridSearcher simplifies running grid searches for machine learning projects in Python, emphasizing parallel execution and GPU scheduling without dependencies on…
      Python
      •
      Apache License 2.0
      •0•5•0•0•Updated Mar 17, 2026Mar 17, 2026

    • llmq

      Public
      Quantized LLM training in pure CUDA/C++.
      cudaquantization-aware-trainingllm-training
      cudaquantization-aware-trainingllm-training
      C++
      •
      Apache License 2.0
      •14•244•0•1•Updated Mar 6, 2026Mar 6, 2026

    • ant

      Public
      🐜 Research-friendly Deep Learning framework
      Python
      •
      MIT License
      •1•0•0•0•Updated Mar 3, 2026Mar 3, 2026

    • FP-Quant

      Public
      Python
      •19•107•13•3•Updated Feb 26, 2026Feb 26, 2026

    • DASH

      Public
      Code for DASH, a faster alternative to Distributed Shampoo via block stacking.
      Python
      •
      MIT License
      •0•9•1•0•Updated Feb 18, 2026Feb 18, 2026

    • MatGPTQ

      Public
      Code for MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
      Python
      •
      MIT License
      •1•18•2•0•Updated Feb 18, 2026Feb 18, 2026

    • PanzaMail

      Public
      Python
      •
      Apache License 2.0
      •22•302•4•7•Updated Feb 15, 2026Feb 15, 2026

    • DASH_DistributedShampoo

      Public
      This repository contains a fork of DistributedShampoo for the DASH project.
      Python
      •
      Other
      •0•0•0•0•Updated Feb 10, 2026Feb 10, 2026

    • ISTA-DASLab-Optimizers-CUDA

      Public
      This repository contains the code for CUDA kernels that support `ISTA-DASLab-Optimizers` project
      Cuda
      •
      MIT License
      •0•0•0•0•Updated Feb 5, 2026Feb 5, 2026

    • behemoth

      Public
      Library for creating synthetic tabular data and converting it to sentences, for training models.
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Feb 2, 2026Feb 2, 2026

    • local_platinum_bench

      Public
      This repo allows you to run Platinum Bench evals via vLLM.
      Python
      •
      Creative Commons Attribution 4.0 International
      •0•0•0•1•Updated Dec 19, 2025Dec 19, 2025

    • MoE-Quant

      Public
      Code for data-aware compression of DeepSeek models
      Python
      •11•72•4•1•Updated Dec 11, 2025Dec 11, 2025

    • QuEST

      Public
      Work in progress.
      Jupyter Notebook
      •
      MIT License
      •9•80•2•0•Updated Nov 25, 2025Nov 25, 2025

    • EvoPress

      Public
      Python
      •
      Apache License 2.0
      •4•41•0•0•Updated Nov 22, 2025Nov 22, 2025

    • nanochat

      Public
      The best ChatGPT that $100 can buy.
      Python
      •
      MIT License
      •7.1k•0•0•0•Updated Nov 12, 2025Nov 12, 2025

    • CAGE

      Public
      Python
      •
      MIT License
      •1•2•0•0•Updated Nov 11, 2025Nov 11, 2025

    • qutlass

      Public
      QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
      cudablackwellquantization-aware-training
      cudablackwellquantization-aware-trainingpost-training-quantization
      C++
      •
      Apache License 2.0
      •22•179•3•1•Updated Nov 11, 2025Nov 11, 2025

    • torchtitan

      Public
      A PyTorch native platform for training generative AI models
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •801•0•0•0•Updated Nov 11, 2025Nov 11, 2025

    • nanochat-qat

      Public
      The best ChatGPT that $100 can buy.
      Python
      •
      MIT License
      •7.1k•1•0•1•Updated Oct 31, 2025Oct 31, 2025

    • CAGE-ao

      Public
      PyTorch native quantization and sparsity for training and inference
      Python
      •
      Other
      •502•0•0•0•Updated Oct 23, 2025Oct 23, 2025

    • unified-sc-laws

      Public
      This repository contains the code for the "Unified Scaling Laws for Compressed Representations" study.
      Python
      •
      MIT License
      •0•0•0•0•Updated Oct 23, 2025Oct 23, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.