Skip to content

@wenxcs-msft wenxcs-msft

Change the repository type filter

All

    Repositories list

    16 repositories

    • public_access_scripts

      Public
      Shell
      •
      Apache License 2.0
      •0•0•1•0•Updated Feb 5, 2025Feb 5, 2025

    • ads-triton-server-third_party

      Public
      Third-party source packages that are modified for use in Triton.
      C
      •
      BSD 3-Clause "New" or "Revised" License
      •59•0•0•0•Updated Jan 28, 2025Jan 28, 2025

    • ads-triton-server

      Public
      The Triton Inference Server provides an optimized cloud and edge inferencing solution.
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •1.5k•0•0•1•Updated Jan 28, 2025Jan 28, 2025

    • vllm-xx

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •5.9k•0•0•8•Updated Sep 26, 2024Sep 26, 2024

    • vllm-pr

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •5.9k•0•0•0•Updated Jul 10, 2024Jul 10, 2024

    • foundation-model-stack

      Public
      Python
      •
      Apache License 2.0
      •62•0•0•0•Updated May 10, 2024May 10, 2024

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •5.9k•0•0•0•Updated May 8, 2024May 8, 2024

    • ads-TensorRT-LLM

      Public
      TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
      C++
      •
      Apache License 2.0
      •1.1k•0•0•0•Updated Jan 26, 2024Jan 26, 2024

    • WizardLM

      Public archive
      WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
      Python
      •731•0•0•0•Updated May 12, 2023May 12, 2023

    • azure-openai-proxy

      Public archive
      A proxy for Azure OpenAI API that can convert an OpenAI request into an Azure OpenAI request.
      Go
      •
      MIT License
      •69•0•0•0•Updated Apr 7, 2023Apr 7, 2023

    • flash-attention-rocm

      Public archive
      Fast and memory-efficient exact attention
      C++
      •
      BSD 3-Clause "New" or "Revised" License
      •1.5k•1•0•0•Updated Feb 25, 2023Feb 25, 2023

    • tvm.dx

      Public archive
      TVM with DirectX support
      Python
      •
      Apache License 2.0
      •1•0•0•1•Updated Dec 12, 2022Dec 12, 2022

    • deort

      Public archive
      Python
      •
      MIT License
      •0•0•0•0•Updated Sep 24, 2022Sep 24, 2022

    • dxpy

      Public archive
      DirectX Python Runtime
      C++
      •
      MIT License
      •0•0•0•0•Updated Apr 3, 2022Apr 3, 2022

    • DirectXShaderCompiler

      Public archive
      This repo hosts the source for the DirectX Shader Compiler which is based on LLVM/Clang.
      C++
      •
      Other
      •722•0•0•1•Updated Mar 26, 2022Mar 26, 2022

    • DirectX-Headers

      Public archive
      Official DirectX headers available under an open source license
      C
      •
      MIT License
      •165•0•0•0•Updated Mar 11, 2022Mar 11, 2022