Triton Model Navigator v0.14.0

• Updates:
  • new: TensorRT INT8 and FP8 quantization through ModelOpt (ONNX path)
  • new: TensorRT NVFP4 quantization through ModelOpt (Torch path)
  • new: Improved TorchCompile performance for repeated compilations using TORCHINDUCTOR_CACHE_DIR environment variable
  • new: Global context with scoped variables - temporary context variables
  • new: Added new context variables INPLACE_OPTIMIZE_WORKSPACE_CONTEXT_KEY and INPLACE_OPTIMIZE_MODULE_GRAPH_ID_CONTEXT_KEY
  • new: nav.bundle.save now has include and exclude patterns for fine grained files selection
  • new: GPU and Host memory usage logging
  • change: Install the TensorRT package for architectures other than x86_64
  • change: Disable conversion fallback for TensorRT paths and expose control option in custom config
  • change: Use torch.export.save for Torch-TRT model serialization
  • change: Added export_engine to OnnxConfig for improved export control
  • fix: Correctness command relative tolerance formula
  • fix: Memory management during export and conversion process for Torch

• Version of external components used during testing:
  • PyTorch 2.7.0a0+7c8ec84dab
  • TensorFlow 2.17.0
  • TensorRT 10.9.0.34
  • TensorRT ModelOptimizer 0.27.0
  • Torch-TensorRT 2.7.0a0
  • ONNX Runtime 1.20.2
  • Polygraphy 0.49.20
  • GraphSurgeon 0.5.8
  • tf2onnx v1.16.1
  • Other component versions depend on the used framework containers versions.
    See its support matrix
    for a detailed summary.