- Sort Score
- Result 10 results
- Languages All
Results 11 - 16 of 16 for tpu_core (0.27 sec)
-
tensorflow/compiler/mlir/tensorflow/transforms/sparsecore/embedding_pipelining.cc
loop_body_func, "sc_forward", &forward_caller, /*flag_for_inlining=*/true); if (failed(result)) return signalPassFailure(); // Create tpu_core function builder.setInsertionPointAfter(forward_caller); TF::StatefulPartitionedCallOp core_tpu_caller = nullptr; result = ExtractOpsAsFunc(builder, module, symbol_table, core_tpu_ops,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 92.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_ops.td
DefaultValuedStrAttr<StrAttr, "">:$send_key, DefaultValuedStrAttr<StrAttr, "">:$recv_key, DefaultValuedOptionalAttr<I64Attr, "1000000">:$cost_estimate_ns, DefaultValuedOptionalAttr<I64Attr, "0">:$tpu_core ); let results = (outs Res<Variadic<TF_Tensor>, [{A list of tensors that will be returned to the device.}]>:$outputs );
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 04:08:35 UTC 2024 - 90.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/g3doc/_includes/tf_passes.md
%2 = "tf.Const"() {value = dense<1.000000e+00> : tensor<f32>} : () -> tensor<f32> %3 = "tf._XlaHostComputeMlir"(%2) {recv_key = "host_compute_channel_0_0_retvals", send_key = "host_compute_channel_0_0_args", tpu_core = 0 : i64} : (tensor<f32>) -> tensor<f32> %4 = "tf.AddV2"(%2, %3) : (tensor<f32>, tensor<f32>) -> tensor<f32> tf_device.return %4 : tensor<f32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Aug 02 02:26:39 UTC 2023 - 96.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/convert_tpu_model_to_cpu.mlir
// RUN: tf-quant-opt %s -quant-convert-tpu-model-to-cpu -inline -quant-cast-bf16-ops-to-f32 -split-input-file | \ // RUN: FileCheck %s // Remove TPU related ops. func.func @tpu_conv(%arg0: tensor<1x3x4x3xf32>) -> tensor<1x3x2x2xf32> { %0 = "tf.TPUOrdinalSelector"() {device = ""} : () -> tensor<?xi32> %1 = "tf.TPUPartitionedCall"(%arg0, %0) {autotuner_thresh = 0 : i64, device = "", f = @tpu_func_0_optim0} : (tensor<1x3x4x3xf32>, tensor<?xi32>) -> tensor<1x3x2x2xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 4.3K bytes - Viewed (0) -
pkg/scheduler/framework/plugins/noderesources/most_allocated_test.go
Type: field.ErrorTypeInvalid, Field: "scoringStrategy.resources[0].weight", }, }, }, { // Bypass extended resource if the pod does not request. // For both nodes: cpuScore and memScore are 50 // Given that extended resource score are intentionally bypassed, // the final scores are: // - node1: (50 + 50) / 2 = 50 // - node2: (50 + 50) / 2 = 50
Registered: Sat Jun 15 01:39:40 UTC 2024 - Last Modified: Fri Dec 15 03:30:06 UTC 2023 - 16K bytes - Viewed (0) -
pkg/scheduler/framework/plugins/noderesources/least_allocated_test.go
Type: field.ErrorTypeInvalid, Field: "scoringStrategy.resources[1].weight", }, }, }, { // Bypass extended resource if the pod does not request. // For both nodes: cpuScore and memScore are 50 // Given that extended resource score are intentionally bypassed, // the final scores are: // - node1: (50 + 50) / 2 = 50 // - node2: (50 + 50) / 2 = 50
Registered: Sat Jun 15 01:39:40 UTC 2024 - Last Modified: Fri Dec 15 03:30:06 UTC 2023 - 18.8K bytes - Viewed (0)