Lines Matching refs:TF

48 graphs, TF-Lite's flat buffer format, TensorFlow's Graph format, the ONNX
78 1.  the TF Lite TOCO translator, which we need to improve error
80 1.  the TF/XLA bridge which needs to improve usability by merging some of its
89 TF Lite is mostly a subset of the larger work to support the functionality of
90 the TF/XLA bridge. TF Lite and the TF/XLA bridge include several compiler passes
134 Dialects (e.g. TF Graph, TF Lite flat buffer, XLA HLO, etc).
197 (e.g. TF Lite when an unsupported op is used) and it is important to be able to
286 introducing a `tf_dead_or<x>` types for switch/merge, modeling of TF operations
292 effort moves beyond TF Lite / TOCO support. The discussions that are happening
342     TensorFlow, TF-Lite, XLA, etc) is all independently selectable by the build
344     they are a TF-Lite system or a client that is completely unrelated to
368 and would provide a path to migrating TF 1.x graphs forward into the TF 2.x
398 there is no runtime component to MLIR: the TensorFlow executor, the TF Lite