Skip to content

Add LiteRT support for Google Tensor chips (Pixel devices) #2

@ivan-digital

Description

@ivan-digital

Context

NNAPI hardware acceleration doesn't work reliably on Google Tensor chips (Pixel 8, 9, 10). The SDK currently falls back to CPU on these devices, which works but is slower than hardware-accelerated inference on Qualcomm/Samsung.

Several Pixel users reported crashes in v0.0.3 (fixed in v0.0.5 with CPU fallback), but performance would benefit from proper hardware acceleration.

Proposal

Add LiteRT (formerly TensorFlow Lite) as an inference backend for Pixel devices, using the GPU delegate for Tensor chip acceleration.

Scope

  • Convert ONNX models to TFLite format (Parakeet TDT, Kokoro, Silero VAD, DeepFilterNet3)
  • Add LiteRT GPU delegate as execution provider alongside ONNX Runtime
  • Auto-detect Tensor SoC and select the right backend
  • Benchmark against CPU-only and NNAPI on Pixel 8/9/10

Affected devices

  • Pixel 8 / 8 Pro (Tensor G3)
  • Pixel 9 / 9 Pro (Tensor G4)
  • Pixel 10 / 10 Pro (Tensor G5)
  • Future Pixel devices

References

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions