Skip to content

@DeepAuto-AI DeepAuto.ai

Change the repository type filter

All

    Repositories list

    6 repositories

    • sglang

      Public
      This is a fork of SGLang for hip-attention integration. Please refer to hip-attention for detail.
      Python
      •
      Apache License 2.0
      •1.1k•11•0•0•Updated Feb 27, 2025Feb 27, 2025

    • hip-attention

      Public
      Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.
      tritonattentionattention-mechanismsub-quadratic-attentionopenai-tritonhip-attention
      Python
      •
      Other
      •13•121•0•0•Updated Feb 25, 2025Feb 25, 2025

    • auto-evolution

      Public
      A framework that encodes and learns from diverse architectures, enabling rapid adaptation, new model generation, and performance gains via latent space exploration.
      Apache License 2.0
      •0•0•0•0•Updated Jan 21, 2025Jan 21, 2025

    • triton

      Public
      Development repository for the Triton language and compiler
      C++
      •
      MIT License
      •1.8k•0•0•0•Updated Oct 11, 2024Oct 11, 2024

    • vllm

      Public
      Up to 4x faster decoding than vLLM using HiP Attention: https://github.com/DeepAuto-AI/hip-attention
      Python
      •
      Apache License 2.0
      •6k•1•0•0•Updated Oct 11, 2024Oct 11, 2024

    • vllm-legacy

      Public
      Forked vLLM Framework, for DeepAuto Chat Platform. Supports HiP Attention
      vllmhip-attention
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Jul 8, 2024Jul 8, 2024