Skip to content

Release v2.3.9

Latest

Choose a tag to compare

@lc700x lc700x released this 03 Feb 12:15
· 2 commits to main since this release

Key Updates

  • Add torch.compile and CuDNN support for AMD ROCm7 supported GPUs with 1.5~2x performance
desktop2stereo_amd_rocm7
  • Add CoreML for Apple Silicon (MPS) devices with 2x performance
desktop2stereo_v2 3 9_mac
  • Enhance the TensorRT performance and compatibility for NVIDIA GPUs (Support more models including DA3MONO, DA3METRIC)
desktop2stereo_nvidia_cuda
  • Add XPU Pytorch backend with OpenVINO optimizer for Intel GPUs. (Better than DirectML, requires 11th Gen and newer iGPUs and dGPUs)
desktop2stereo_intel_xpu
  • Enable automatic inference optimizer options for supported hardware
  • Enable GPU OpenCL acceleration for the Screen Capture process with lower CPU usage
  • Change RTMP server backend with SRT protocol on Windows with lower latency on supported RTSP and WebRTC clients
  • Correct depth calculation and normalization for DA3 and metric models
  • Update ROCm7 hardware installation script with official ROCm7.2 (9700/9070/9060/7900/7800/7700/840M/860M/880M/890M/8060s) and TheRock 7.1.2 for (Almost all RDNA2/3/4 GPU/APUs)
  • Fix Video Depth Anything torch.compile failure and enable DA3-Small/Base/Large/Giant tensorrt support

Performance Benchmark

Desktop2Stereo Performance Win/Mac

Alternative Download Link