Skip to content

@vectorch-ai Vectorch AI

Change the repository type filter

All

    Repositories list

    16 repositories

    • ScaleLLM

      Public
      A high-performance inference system for large language models, designed for production environments.
      performancegpumodelproductioncudaefficiencyinferencetransformerllamaspeculative
      C++
      •
      Apache License 2.0
      •37•488•48•8•Updated Dec 19, 2025Dec 19, 2025

    • cutlass

      Public
      CUDA Templates for Linear Algebra Subroutines
      C++
      •
      Other
      •1.6k•0•0•0•Updated Nov 6, 2025Nov 6, 2025

    • nixl

      Public
      NVIDIA Inference Xfer Library (NIXL)
      C++
      •
      Apache License 2.0
      •208•0•0•0•Updated Nov 4, 2025Nov 4, 2025

    • dynamo

      Public
      A Datacenter Scale Distributed Inference Serving Framework
      Rust
      •
      Apache License 2.0
      •748•0•0•0•Updated Nov 4, 2025Nov 4, 2025

    • whl

      Public
      repository to host python whl package.
      HTML
      •0•0•0•0•Updated Sep 13, 2025Sep 13, 2025

    • flux

      Public
      A fast communication-overlapping library for tensor/expert parallelism on GPUs.
      C++
      •
      Apache License 2.0
      •85•0•0•0•Updated Apr 15, 2025Apr 15, 2025

    • 3FS

      Public
      A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
      C++
      •
      MIT License
      •977•0•0•0•Updated Feb 28, 2025Feb 28, 2025

    • flashinfer

      Public
      FlashInfer: Kernel Library for LLM Serving
      Cuda
      •
      Apache License 2.0
      •606•0•0•0•Updated Feb 27, 2025Feb 27, 2025

    • FlashMLA

      Public
      C++
      •
      MIT License
      •918•0•0•0•Updated Feb 26, 2025Feb 26, 2025

    • vcpkg

      Public
      C++ Library Manager for Windows, Linux, and MacOS
      CMake
      •
      MIT License
      •7.3k•0•0•0•Updated Feb 24, 2025Feb 24, 2025

    • discussions

      Public
      0•0•0•0•Updated Jun 5, 2024Jun 5, 2024

    • flash-attention

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •2.2k•0•0•0•Updated Oct 15, 2023Oct 15, 2023

    • tokenizers

      Public
      💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
      Rust
      •
      Apache License 2.0
      •1k•0•0•0•Updated Aug 4, 2023Aug 4, 2023

    • xformers

      Public
      Hackable and optimized Transformers building blocks, supporting a composable construction.
      Python
      •
      Other
      •746•0•0•0•Updated Aug 1, 2023Aug 1, 2023

    • FasterTransformer

      Public
      Transformer related optimization, including BERT, GPT
      C++
      •
      Apache License 2.0
      •927•0•0•0•Updated Jul 28, 2023Jul 28, 2023

    • ByteTransformer

      Public
      optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
      C++
      •
      Apache License 2.0
      •37•0•0•0•Updated Jul 24, 2023Jul 24, 2023