Skip to content

@krai KRAI

Change the repository type filter

All

    Repositories list

    43 repositories

    • axs

      Public
      KRAI X workflow automation system
      Python
      •
      MIT License
      •2•4•0•1•Updated Nov 18, 2024Nov 18, 2024

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •4.6k•0•0•0•Updated Nov 15, 2024Nov 15, 2024

    • axs2mlperf

      Public
      Automated KRAI X workflows for reproducing MLPerf Inference submissions
      Python
      •
      MIT License
      •1•1•11•1•Updated Nov 13, 2024Nov 13, 2024

    • kilt4uai

      Public
      A plugin for KILT (KRAI Inference Library Technology) for integration with Untether AI's imAIgine SDK
      C++
      •
      MIT License
      •0•0•0•0•Updated Aug 6, 2024Aug 6, 2024

    • axs2uai

      Public
      Automated KRAI X workflows for reproducing MLPerf Inference submissions on systems with Untether AI's speedAI at-memory compute inference accelerators
      Python
      •
      MIT License
      •0•0•0•0•Updated Aug 6, 2024Aug 6, 2024

    • axs2onnxrt

      Public
      Automated KRAI X workflows for reproducing MLPerf Inference submissions on systems withAutomated KRAI X workflows for reproducing MLPerf Inference submissions with KILT ONNXRT CPU/GPU backends
      MIT License
      •0•0•0•0•Updated Jul 26, 2024Jul 26, 2024

    • axs2kilt

      Public
      Automated KRAI X workflows for reproducing MLPerf Inference submissions powered by KRAI Inference Library Technology (KILT)
      Python
      •
      MIT License
      •1•1•0•0•Updated Jul 26, 2024Jul 26, 2024

    • axs2system

      Public
      Automated KRAI X workflows for reproducing MLPerf Inference submissions
      Python
      •
      MIT License
      •0•0•0•0•Updated Jul 26, 2024Jul 26, 2024

    • kilt-mlperf

      Public
      KILT (KRAI Inference Library Technology) - proudly powering some of the fastest and most energy efficient submissions in the history of MLPerf Inference
      C++
      •
      MIT License
      •1•1•0•0•Updated Jul 26, 2024Jul 26, 2024

    • inference

      Public
      Reference implementations of inference benchmarks
      Python
      •
      Apache License 2.0
      •536•0•0•0•Updated Jun 21, 2024Jun 21, 2024

    • policies

      Public
      General policies for MLPerf™ including submission rules, coding standards, etc.
      Python
      •
      Apache License 2.0
      •54•0•0•0•Updated Jun 11, 2024Jun 11, 2024

    • axs2qaic

      Public
      Automated KRAI X workflows for reproducing MLPerf Inference submissions on systems equipped with Qualcomm Cloud AI 100 accelerators
      Python
      •
      MIT License
      •0•0•0•0•Updated Apr 10, 2024Apr 10, 2024

    • axs2qaic-docker

      Public
      Building Docker images for reproducing MLPerf Inference submissions with Qualcomm Cloud AI 100 accelerators
      Shell
      •
      Other
      •0•0•0•0•Updated Apr 10, 2024Apr 10, 2024

    • inference_policies

      Public
      Issues related to MLPerf™ Inference policies, including rules and suggested changes
      Apache License 2.0
      •52•0•0•0•Updated Apr 2, 2024Apr 2, 2024

    • axs2gcp

      Public
      Automated KRAI X workflows for Google Cloud Platform
      google-cloudgoogle-cloud-platformgoogle-benchmarktputpu-benchmarkstpu-accelerationmlperf-inferencetpu-vmgptjtpu-optimization
      Python
      •
      MIT License
      •0•3•0•0•Updated Mar 14, 2024Mar 14, 2024

    • cloud-ai-sdk

      Public
      Qualcomm Cloud AI SDK (Platform and Apps) enable high performance deep learning inference on Qualcomm Cloud AI platforms delivering high throughput and low latency across Computer Vision, Object Detection, Natural Language Processing and Generative AI models.
      Jupyter Notebook
      •
      Other
      •7•0•0•0•Updated Mar 12, 2024Mar 12, 2024

    • axs2config

      Public
      MIT License
      •0•0•0•0•Updated Jan 29, 2024Jan 29, 2024

    • power-dev

      Public
      Dev repo for power measurement for the MLPerf benchmarks
      Python
      •
      Apache License 2.0
      •24•0•0•0•Updated Jan 26, 2024Jan 26, 2024

    • LLM_Wiki

      Public
      This is just a place for us to put whatever we’ve learnt about LLMs, be it papers, blog posts or our own experiences.
      0•1•0•0•Updated Nov 29, 2023Nov 29, 2023

    • TextToJSONConverter

      Public
      TextToJSONConverter
      HTML
      •0•0•0•0•Updated Oct 25, 2023Oct 25, 2023

    • MultilineToOneLiner

      Public
      TextLineConverter for NLP
      HTML
      •0•0•0•0•Updated Oct 25, 2023Oct 25, 2023

    • inference_results_v3.1

      Public
      This repository contains the results and code for the MLPerf™ Inference v3.1 benchmark.
      Apache License 2.0
      •13•0•0•0•Updated Oct 10, 2023Oct 10, 2023

    • nn_pruning-dev

      Public
      Prune a model while finetuning or training.
      Jupyter Notebook
      •
      Apache License 2.0
      •58•0•0•0•Updated Sep 26, 2023Sep 26, 2023

    • axs2snpe

      Public
      MIT License
      •0•0•0•0•Updated Sep 5, 2023Sep 5, 2023

    • axs2tensorrt

      Public
      Python
      •
      MIT License
      •0•0•0•0•Updated Aug 18, 2023Aug 18, 2023

    • ck-mlperf

      Public archive
      Automated workflows for MLPerf, the industry-leading benchmark for evaluating performance of ML software and hardware
      Jupyter Notebook
      •
      BSD 3-Clause "New" or "Revised" License
      •23•4•0•0•Updated Aug 1, 2023Aug 1, 2023

    • bert_pruners

      Public
      Python
      •0•0•1•0•Updated Jun 9, 2023Jun 9, 2023

    • ck-qaic

      Public archive
      Qualcomm Cloud AI (QAIC) implementation of MLPerf Inference benchmarks
      C++
      •5•8•0•0•Updated Jun 7, 2023Jun 7, 2023

    • ck-armnn

      Public archive
      Collective Knowledge workflows for ArmNN
      Shell
      •
      BSD 3-Clause "New" or "Revised" License
      •10•1•1•0•Updated Apr 3, 2023Apr 3, 2023

    • axs2kilt_v3.0

      Public
      axs repository for KILT
      Python
      •
      MIT License
      •0•1•0•0•Updated Mar 7, 2023Mar 7, 2023