- 30 8月, 2023 40 次提交
-
-
由 Pratik Joshi 提交于
The line ``` segmentation_options = processor.SegmentationOptions( output_type=processor.SegmentationOptions.OutputType.CATEGORY_MASK) ``` is changed to ``` segmentation_options = processor.SegmentationOptions( output_type=processor.SegmentationOptions.output_type.CATEGORY_MASK) ```
-
由 Adrian Kuegel 提交于
After scheduling, it is possible to eliminate more copies that have been added by the CopyInsertion pass, because now it is clear in which order the operations are executed. PiperOrigin-RevId: 561300243
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561283397
-
由 Alan Kelly 提交于
PiperOrigin-RevId: 561274977
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561272373
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561272265
-
由 Alan Kelly 提交于
PiperOrigin-RevId: 561263745
-
由 Dan Suh 提交于
Add implementations to handle the case where the calibration wrapper accepts a TFLite flatbuffer model that uses offset buffers. Offset buffers are enabled by the TFLite converter's `_experimental_use_buffer_offset` flag. Whenever the model's base buffer (that contains the serialized flatbuffer) is modified, the offset values to the offset buffer of the tensor buffers should be updated. PiperOrigin-RevId: 561251067
-
由 Kyuyeun Kim 提交于
Per-layer verify creates a model with both quantized and original unquantized layer. Unquantized layer's input comes from previous layer's quantized layer. Outputs of quantized and unquantized layers are saved via DumpTensorOp PiperOrigin-RevId: 561233115
-
由 Kyuyeun Kim 提交于
DumpTensorOp saves entire value of quantizable layer during inference. Whole model verify creates two models: 1. Unquantized model with DumpTensorOp - saved at unquantized_dump_model_path 2. Quantized model with DumpTensorOp - saved at output_directory of quantized model PiperOrigin-RevId: 561222579
-
由 Majid Dadashi 提交于
PiperOrigin-RevId: 561220243
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561208020
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561206751
-
由 Haoliang Zhang 提交于
PiperOrigin-RevId: 561205731
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561195486
-
由 A. Unique TensorFlower 提交于
Updates LLVM usage to match [96e83d3705c7](https://github.com/llvm/llvm-project/commit/96e83d3705c7) PiperOrigin-RevId: 561194584
-
由 TensorFlower Gardener 提交于
PiperOrigin-RevId: 561192100
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561188743
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561184976
-
由 Fiona Lang 提交于
PiperOrigin-RevId: 561183522
-
由 Haoliang Zhang 提交于
PiperOrigin-RevId: 561183306
-
由 Luke Boyer 提交于
DataRef implementation to wrap tflite tensors. This lets us interop cleanly with the tflite memory system within out functions. PiperOrigin-RevId: 561180210
-
由 Adam Cogdell 提交于
PiperOrigin-RevId: 561178670
-
由 Skye Wanderman-Milne 提交于
See https://dmlc.github.io/dlpack/latest/python_spec.html. This is the import path. The export path was implemented in https://github.com/openxla/xla/commit/0b3cbfe4bc7cd68dc20924bd878cdfb2faa1a169. This allows for creating jax.Arrays from external GPU arrays asynchronously. PiperOrigin-RevId: 561172624
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561168251
-
由 Skye Wanderman-Milne 提交于
* Rearrange PJRT_Api struct before major version bump * Return unimplemented instead of nullptr PiperOrigin-RevId: 561165318
-
由 Tianrun Li 提交于
Temporarily disable LaxBackedNumpyTests.testSortKeyValue_(2,3,4)_float32_bool_1 to pass TF nightly build PiperOrigin-RevId: 561163175
-
由 Sandeep Dasgupta 提交于
PiperOrigin-RevId: 561161226
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561150086
-
由 Adam Cogdell 提交于
PiperOrigin-RevId: 561148975
-
由 Skye Wanderman-Milne 提交于
This changes removes `PJRT_Buffer_OnDeviceTrimmedShape` and related functionality, since passing around xla::Shapes is expensive and often includes more information than is necessary or even meaningful, and we now have more specific getters that should be used instead. This means that `PjRtBuffer::on_device_shape` and `PjRtBuffer:logical_on_device_shape` no longer work with the PjRtCApiClient. Instead, C++ callers should use the new more-specific getters: * `PjRtBuffer::element_type()` * `PjRtBuffer::dimensions()` * `PjRtBuffer::layout()` * `PjRtBuffer::has_dynamic_dimensions()` * `PjRtBuffer::is_dynamic_dimension()` * `PjRtBuffer::logical_dimensions()` These all have corresponding C APIs. PiperOrigin-RevId: 561148407
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561141352
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561137986
-
由 Kevin Chen 提交于
Broke argsort on gpu. PiperOrigin-RevId: 561136138
-
https://github.com/tensorflow/tensorflow/pull/59974由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561134835
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561134253
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561126894
-
由 Peter Hawkins 提交于
JAX CI started failing with: ``` external/xla/xla/service/gpu/fusion_pipeline.cc:85:10: error: use of deleted function 'xla::HloPassPipeline::HloPassPipeline(const xla::HloPassPipeline&)' 85 | return fusion; | ^~~~~~ In file included from external/xla/xla/service/gpu/fusion_pipeline.h:21, from external/xla/xla/service/gpu/fusion_pipeline.cc:16: external/xla/xla/service/hlo_pass_pipeline.h:36:7: note: 'xla::HloPassPipeline::HloPassPipeline(const xla::HloPassPipeline&)' is implicitly deleted because the default definition would be ill-formed: 36 | class HloPassPipeline : public HloPassInterface { | ^~~~~~~~~~~~~~~ external/xla/xla/service/hlo_pass_pipeline.h:36:7: error: use of deleted function 'std::unique_ptr<_Tp, _Dp>::unique_ptr(const std::unique_ptr<_Tp, _Dp>&) [with _Tp = xla::CompilationStats; _Dp = std::default_delete<xla::CompilationStats>]' In file included from /dt9/usr/bin/../lib/gcc/x86_64-pc-linux-gnu/9/../../../../include/c++/9/memory:80, from external/xla/xla/stream_executor/device_description.h:25, from external/xla/xla/service/gpu/gpu_types.h:21, from external/xla/xla/service/gpu/gpu_device_info.h:22, from external/xla/xla/service/gpu/fusion_pipeline.h:19, from external/xla/xla/service/gpu/fusion_pipeline.cc:16: /dt9/usr/bin/../lib/gcc/x86_64-pc-linux-gnu/9/../../../../include/c++/9/bits/unique_ptr.h:414:7: note: declared here 414 | unique_ptr(const unique_ptr&) = delete; | ^~~~~~~~~~ external/xla/xla/service/gpu/fusion_pipeline.cc: In function 'xla::HloPassPipeline xla::gpu::HorizontalFusionPipeline(const xla::gpu::GpuDeviceInfo&)': external/xla/xla/service/gpu/fusion_pipeline.cc:96:10: error: use of deleted function 'xla::HloPassPipeline::HloPassPipeline(const xla::HloPassPipeline&)' 96 | return horizontal_fusion; | ^~~~~~~~~~~~~~~~~ ``` I'm guessing this is just GCC having a slightly different interpretation of whether this needs a copy. PiperOrigin-RevId: 561123362
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 561114720
-
由 Faizan Muhammad 提交于
PiperOrigin-RevId: 561111836
-