Skip to content

@IST-DASLab IST Austria Distributed Algorithms and Systems Lab

Change the repository type filter

All

    Repositories list

    72 repositories

    • llmq

      Public
      Quantized LLM training in pure CUDA/C++.
      cudaquantization-aware-trainingllm-training
      C++
      •
      Apache License 2.0
      •14•224•0•0•Updated Dec 19, 2025Dec 19, 2025

    • 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
      •10•66•3•1•Updated Dec 11, 2025Dec 11, 2025

    • QuEST

      Public
      Work in progress.
      Jupyter Notebook
      •
      MIT License
      •7•76•2•0•Updated Nov 25, 2025Nov 25, 2025

    • EvoPress

      Public
      Python
      •
      Apache License 2.0
      •4•38•1•0•Updated Nov 22, 2025Nov 22, 2025

    • Quartet

      Public
      Jupyter Notebook
      •
      MIT License
      •11•113•2•0•Updated Nov 18, 2025Nov 18, 2025

    • FP-Quant

      Public
      Python
      •13•89•7•3•Updated Nov 16, 2025Nov 16, 2025

    • GridSearcher

      Public
      GridSearcher simplifies running grid searches for machine learning projects in Python, emphasizing parallel execution and GPU scheduling without dependencies on SLURM or other workload managers.
      Python
      •
      Apache License 2.0
      •0•3•0•0•Updated Nov 14, 2025Nov 14, 2025

    • nanochat

      Public
      The best ChatGPT that $100 can buy.
      Python
      •
      MIT License
      •5k•0•0•0•Updated Nov 12, 2025Nov 12, 2025

    • CAGE

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

    • qutlass

      Public
      QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
      cudablackwellquantization-aware-trainingpost-training-quantization
      C++
      •
      Apache License 2.0
      •14•149•2•0•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
      •653•0•0•0•Updated Nov 11, 2025Nov 11, 2025

    • nanochat-qat

      Public
      The best ChatGPT that $100 can buy.
      Python
      •
      MIT License
      •5k•1•0•1•Updated Oct 31, 2025Oct 31, 2025

    • CAGE-ao

      Public
      PyTorch native quantization and sparsity for training and inference
      Python
      •
      Other
      •389•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

    • ISTA-DASLab-Optimizers

      Public
      Python
      •
      Apache License 2.0
      •0•11•0•0•Updated Oct 8, 2025Oct 8, 2025

    • gptq-gguf-toolkit

      Public
      Efficient non-uniform quantization with GPTQ for GGUF
      Python
      •4•57•0•1•Updated Sep 17, 2025Sep 17, 2025

    • Yolov8-Pose-Detection-on-Browser

      Public
      Example of YOLOv8 pose detection (estimation) on browser. It shows implementations powered by ONNX and TFJS served through JavaScript without any frameworks. It demonstrates pose detection (estimation) on image as well as live web camera,
      HTML
      •
      MIT License
      •4•0•0•0•Updated Jun 13, 2025Jun 13, 2025

    • influence_distillation

      Public
      Official implementation of Influence Distillation: https://www.arxiv.org/abs/2505.19051
      Python
      •0•3•1•0•Updated May 29, 2025May 29, 2025

    • PanzaMail

      Public
      Python
      •
      Apache License 2.0
      •19•298•4•6•Updated Apr 8, 2025Apr 8, 2025

    • HALO-anon

      Public
      0•0•0•0•Updated Apr 1, 2025Apr 1, 2025

    • torch_cgx

      Public
      Pytorch distributed backend extension with compression support
      C++
      •
      GNU Affero General Public License v3.0
      •0•16•4•0•Updated Mar 24, 2025Mar 24, 2025

    • gemm-int8

      Public
      High Performance Int8 GEMM Kernels for SM80 and later GPUs.
      Python
      •
      MIT License
      •0•18•0•0•Updated Mar 11, 2025Mar 11, 2025

    • DarwinLM

      Public
      Official Pytorch Implementation of Paper "DarwinLM: Evolutionary Structured Pruning of Large Language Models"
      Python
      •3•20•0•0•Updated Feb 21, 2025Feb 21, 2025

    • ScalableMNN

      Public
      Official Repository for "Scalable Mechanistic Neural Networks" (ICLR 2025)
      Python
      •
      MIT License
      •0•2•0•0•Updated Feb 19, 2025Feb 19, 2025

    • SPADE

      Public
      Code of SPADE: Sparsity Guided Debugging for Deep Neural Networks
      Jupyter Notebook
      •3•1•1•0•Updated Feb 18, 2025Feb 18, 2025

    • HALO

      Public
      HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arxiv.org/abs/2501.02625
      Python
      •
      MIT License
      •0•29•1•0•Updated Feb 17, 2025Feb 17, 2025

    • gemm-fp8

      Public
      High Performance FP8 GEMM Kernels for SM89 and later GPUs.
      Cuda
      •
      MIT License
      •1•20•0•0•Updated Jan 24, 2025Jan 24, 2025

    • MicroAdam

      Public
      This repository contains code for the MicroAdam paper.
      Python
      •
      Apache License 2.0
      •4•21•1•0•Updated Dec 14, 2024Dec 14, 2024

    • llm-foundry

      Public
      LLM training code for Databricks foundation models
      Python
      •
      Apache License 2.0
      •580•0•0•1•Updated Nov 27, 2024Nov 27, 2024