- Sort Score
- Result 10 results
- Languages All
Results 11 - 13 of 13 for PartitionedCall (0.16 sec)
-
tensorflow/compiler/jit/ops/xla_ops.cc
.SetShapeFn([](InferenceContext* c) { c->set_output(0, c->input(0)); return absl::OkStatus(); }) .Doc(R"(XLA Merge Op. For use by the XLA JIT only. Merges the outputs from the PartitionedCall node and the _XlaRun node. Unlike the TensorFlow Merge op, which requires inputs of some types to be placed on the host, the _XlaMerge op can merge inputs of all types when
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Sat Apr 06 09:08:06 UTC 2024 - 4.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/quantize.mlir
// CHECK-NEXT: [[q_bias:%.+]] = "quantfork.qcast"([[bias]]) : (tensor<2xf32>) -> tensor<2x!quant.uniform<i32:f32, 0.044022349891595126>>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 19:32:28 UTC 2024 - 6.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/lift_hashtable_ops_as_args.cc
return true; } } return false; } // Checks if the function is only used by supported ops. Returns false when the // function has no uses. Currently, only PartitionedCall is supported. // TODO(b/284222309): Support lifting for functions called by control flow. bool UsedBySupportedOps(ModuleOp module, func::FuncOp func) { auto function_uses =
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 17:58:54 UTC 2024 - 8.2K bytes - Viewed (0)