Search Options

Display Count
Sort
Preferred Language
Advanced Search

Results 1 - 1 of 1 for FP16 (0.07 seconds)

  2. github.com/tensorflow/tensorflow

    RELEASE.md 

            INT8 types for weights and will only be executable interpreters from
        this version onwards.
    *   Post-training quantization tool supports fp16 weights and GPU delegate
        acceleration for fp16.
    *   Add delegate support for `QUANTIZED_16BIT_LSTM`.
    *   Extracts `NNAPIDelegateKernel` from nnapi_delegate.cc

*   TensorRT
    Created: Tue Apr 07 12:39:13 GMT 2026
    - Last Modified: Mon Mar 30 18:31:38 GMT 2026
    - 746.5K bytes
    - Click Count (3)
Back to Top