-
Notifications
You must be signed in to change notification settings - Fork 576
Insights: pytorch/executorch
Overview
Could not load contribution data
Please try again later
123 Pull requests merged by 41 people
-
[ET-VK] Migrate ops to use
DynamicDispatchNode#11353 merged
Jun 4, 2025 -
[ET-VK] Migrate ops to use
DynamicDispatchNode#11312 merged
Jun 4, 2025 -
bump torchao pin
#11340 merged
Jun 4, 2025 -
Switch fbcode builds of ExecuTorch and PyTorch to fbsource sleef
#11261 merged
Jun 4, 2025 -
irangeify most of runtime/core/exec_aten
#8612 merged
Jun 4, 2025 -
[ET-VK][ez] Fix handling of assert ops
#11349 merged
Jun 4, 2025 -
[ET-VK][Ops] aten.tan.default from scratch implementation
#11152 merged
Jun 4, 2025 -
Dtype selective build: disable when not in xplat and add fail msg
#11219 merged
Jun 4, 2025 -
[ET-VK] Add support for binary symint ops
#11348 merged
Jun 4, 2025 -
[ET-VK] Add reshape functions for transformers related operators
#11347 merged
Jun 4, 2025 -
Reusable test framework the Inspector tests
#11314 merged
Jun 4, 2025 -
[ET-VK][ez] Fix handling of assert ops
#11258 merged
Jun 4, 2025 -
[ET-VK] Add support for binary symint ops
#11257 merged
Jun 4, 2025 -
[ET-VK] Add reshape functions for transformers related operators
#11256 merged
Jun 4, 2025 -
Removing uneeded buck deps in cmake build flow
#11315 merged
Jun 3, 2025 -
Mitigate coremltool issue with python 3.13
#11317 merged
Jun 3, 2025 -
Consolidating executor runners in CMake - xnnpack
#11239 merged
Jun 3, 2025 -
[ET-VK] Using push constants for buffer to image prepack nodes.
#11308 merged
Jun 3, 2025 -
Arm Backend: Remove unused param in aot_arm_compiler.py
#10970 merged
Jun 3, 2025 -
Bump tokenizers
#11300 merged
Jun 3, 2025 -
Remove remaining reference to torchgen.gen_executorch
#11290 merged
Jun 3, 2025 -
[ET-VK] Using push constants for buffer to image prepack nodes.
#11252 merged
Jun 3, 2025 -
removing 8da4w-gptq
#11274 merged
Jun 3, 2025 -
serialize scales as bf16 and serialize in Named Data Map
#11031 merged
Jun 3, 2025 -
Update cpuinfo utils to account for apple soc detection
#11268 merged
Jun 3, 2025 -
Make the intermediate output capturer more extensible
#11289 merged
Jun 3, 2025 -
[ET-VK] Introduce generalized shaders for transfer ops and use it for select and slice
#11304 merged
Jun 3, 2025 -
[ET-VK][ez] Updates to DynamicDispatchNode
#11303 merged
Jun 3, 2025 -
[ET-VK][ez] Enable dynamic shape support when using push constants
#11302 merged
Jun 3, 2025 -
Fix output spec + insert clone for constant_prop_pass.
#11209 merged
Jun 3, 2025 -
[ET-VK] Introduce generalized shaders for transfer ops and use it for select and slice
#11255 merged
Jun 2, 2025 -
[ET-VK][ez] Updates to DynamicDispatchNode
#11254 merged
Jun 2, 2025 -
[ET-VK][ez] Enable dynamic shape support when using push constants
#11253 merged
Jun 2, 2025 -
Support approximate gelu
#11246 merged
Jun 2, 2025 -
[llama examples] Update README.md to refer directly consolidated.00.p…
#11298 merged
Jun 2, 2025 -
Make release labels optional
#11291 merged
Jun 2, 2025 -
Qualcomm AI Engine Direct - GA Model Enablement (deit)
#11065 merged
Jun 2, 2025 -
Make release labels optional
#11287 merged
Jun 2, 2025 -
Update discord link
#11243 merged
Jun 2, 2025 -
Use GraphBuilder in memory passes unit tests. # 1
#11265 merged
Jun 2, 2025 -
Arm backend: TOSA 1.0 fixes
#11284 merged
Jun 2, 2025 -
Removed minimum target macOS 11.0 branching
#11266 merged
Jun 2, 2025 -
Arm backend: aot_arm_compiler.py: Create output dir
#11282 merged
Jun 2, 2025 -
Arm backend: Reduce atol in vector_norm test
#11281 merged
Jun 2, 2025 -
Arm backend: Make pre-push non-interactive on one argument
#11280 merged
Jun 2, 2025 -
Arm backend: Add TOSA support for GroupNorm
#10198 merged
Jun 2, 2025 -
Qualcomm AI Engine Direct - Fix error of avg pool2d
#11275 merged
Jun 2, 2025 -
Qualcomm AI Engine Direct - Add rewrite function of observer
#10093 merged
Jun 2, 2025 -
Add support for bias in optimized op_linear.cpp.
#11210 merged
May 31, 2025 -
: Adds DSP op for RoPE
#11264 merged
May 31, 2025 -
Add portable randn kernel implementation
#11123 merged
May 31, 2025 -
[ET-VK] Fixing out_limits_scaled calculation for conv2d pw ops.
#11271 merged
May 31, 2025 -
[ET-VK] Removed shared memory usage and simplied conv2d dw op shader to improve performance.
#11270 merged
May 31, 2025 -
Remove the ability to choose pybinding when installing ExecuTorch
#11233 merged
May 30, 2025 -
Add portable rand kernel implementation
#11127 merged
May 30, 2025 -
[ET-VK] Fixing out_limits_scaled calculation for conv2d pw ops.
#11251 merged
May 30, 2025 -
[ET-VK] Removed shared memory usage and simplied conv2d dw op shader to improve performance.
#11178 merged
May 30, 2025 -
Update cpuinfo commit to include new apple soc info
#11262 merged
May 30, 2025 -
[ET-VK][Ops] Registering tan tests
#11220 merged
May 30, 2025 -
fix where self out contraint to make a, b numerical
#11240 merged
May 30, 2025 -
Disable ReplaceConvWithChannelLastConvPass.
#11211 merged
May 30, 2025 -
Use new APIs in TensorTest.swift
#11248 merged
May 30, 2025 -
Bump macOS deployment target to 12.0
#11247 merged
May 30, 2025 -
Where layer
#11181 merged
May 30, 2025 -
Save the representative intputs into the ETRecord object
#11244 merged
May 30, 2025 -
Export recipe changes for export_llama integration
#11227 merged
May 30, 2025 -
Add event_tracer to MIL for Backend Init Context
#11105 merged
May 30, 2025 -
Used cmake-format on CMakeLists.txt
#11230 merged
May 30, 2025 -
Remove MPS backend dependencies installation
#11237 merged
May 30, 2025 -
Use lateinit var to remove !! and created a common TestFileUtils
#11155 merged
May 30, 2025 -
Enable OSS coreml python tests
#10975 merged
May 30, 2025 -
Update the image listing the apple frameworks
#11234 merged
May 29, 2025 -
Qualcomm AI Engine Direct - GA efficientnet
#11212 merged
May 29, 2025 -
[ET-VK] Applying bias after sum calculation in conv2d pw shader to improve performance.
#11193 merged
May 29, 2025 -
Retire kernels_portable framework in favor of kernels_optimized
#11226 merged
May 29, 2025 -
Revert D75313723: Extract DeviceType to a standalone header file
#11224 merged
May 29, 2025 -
Update Package.swift to match the template in swiftpm branch
#11223 merged
May 29, 2025 -
[ET-VK] Reducing precision of some in members in conv2d pw to improved performance.
#11192 merged
May 29, 2025 -
[ET-VK][Ops] Registering tan tests
#11216 merged
May 29, 2025 -
forward fix uninitialized param
#11218 merged
May 29, 2025 -
Qualcomm AI Engine Direct - GA PVT
#11035 merged
May 29, 2025 -
Dtype selective build: disable when not in xplat and add fail msg
#11090 merged
May 29, 2025 -
Create the
IntermediateOutputCapturerClass to Store the IntermediateOutput of the AOT Graph#11202 merged
May 29, 2025 -
[ET-VK] Storing positions in uint16 to instead of int in conv2d pw shader.
#11191 merged
May 29, 2025 -
[ET-VK] Creating specialized version of conv2d pw shader for X and Y stride = 1 and padding = 0.
#11190 merged
May 29, 2025 -
Move googletest inclusion to third-party
#11207 merged
May 29, 2025 -
Replace manual pointer alignment with std::aligned_alloc
#11203 merged
May 29, 2025 -
[ET-VK] De vectorise all vectors in conv2d pw shader to improve perf.
#11189 merged
May 29, 2025 -
[ET-VK] Tuning local workgroup size calculation for conv2d pw to improve performance.
#11188 merged
May 29, 2025 -
Migrate pt2e qualcomm
#11049 merged
May 29, 2025 -
Use single_op_builder in simplify unit tests.
#11158 merged
May 29, 2025 -
Fix EXIR doc typo.
#11008 merged
May 28, 2025 -
[ET-VK] Minor unroll tuning to improve conv2d pw perf.
#11187 merged
May 28, 2025 -
Support CoreML export on Linux
#11172 merged
May 28, 2025 -
Skip ExportLlamaLibTest
#11201 merged
May 28, 2025 -
Fix calibration data propagation
#11195 merged
May 28, 2025 -
Migrate pt2e arm
#11053 merged
May 28, 2025 -
[ET-VK] De vectorise positions in conv2d pw shader to improve perf.
#11186 merged
May 28, 2025 -
Fix triu/tril CoreML lowering error in to_edge_transform_and_lower
#11107 merged
May 28, 2025 -
Update apple.yml
#11200 merged
May 28, 2025 -
Use GraphBuilder in test fusion ops.
#11078 merged
May 28, 2025 -
[ET-VK] Minor tuning for conv2d pw op to improve performance.
#11185 merged
May 28, 2025 -
[ET-VK] Tuning conv 2d pw op tile size to improve perf.
#11184 merged
May 28, 2025 -
[ET-VK] Remove the use of shared memory in conv2d pw to improve perf.
#11183 merged
May 28, 2025 -
Share threadpool framework between xnnpack and optimized kernels
#11194 merged
May 28, 2025 -
Rename Apple simulator libs to maintain backwards compatibility
#11196 merged
May 28, 2025 -
Add GELU support to XNNPACK
#11006 merged
May 28, 2025 -
[ET-VK] De vectorise conv2d pw shader to improve perf.
#11182 merged
May 28, 2025 -
Update docs for simple usage of scripts/build_apple_frameworks.sh
#11174 merged
May 28, 2025 -
[ET-VK] Applying bias after sum calculation in conv2d pw shader to improve performance.
#11150 merged
May 28, 2025 -
[ET-VK] Reducing precision of some in members in conv2d pw to improved performance.
#11139 merged
May 28, 2025 -
[ET-VK] Storing positions in uint16 to instead of int in conv2d pw shader.
#11138 merged
May 28, 2025 -
[ET-VK] Creating specialized version of conv2d pw shader for X and Y stride = 1 and padding = 0.
#11137 merged
May 28, 2025 -
[ET-VK] De vectorise all vectors in conv2d pw shader to improve perf.
#11136 merged
May 28, 2025 -
[ET-VK] Tuning local workgroup size calculation for conv2d pw to improve performance.
#11135 merged
May 28, 2025 -
[ET-VK] Minor unroll tuning to improve conv2d pw perf.
#11134 merged
May 28, 2025 -
[ET-VK] De vectorise positions in conv2d pw shader to improve perf.
#11122 merged
May 28, 2025 -
[ET-VK] Minor tuning for conv2d pw op to improve performance.
#11113 merged
May 28, 2025 -
[ET-VK] Tuning conv 2d pw op tile size to improve perf.
#11112 merged
May 28, 2025 -
[ET-VK] Remove the use of shared memory in conv2d pw to improve perf.
#11110 merged
May 28, 2025 -
[ET-VK] De vectorise conv2d pw shader to improve perf.
#11108 merged
May 28, 2025
54 Pull requests opened by 34 people
-
[ET-VK][Ops] aten.var.dim from scratch implementation
#11197 opened
May 28, 2025 -
[ET-VK][Ops] aten.var.dim in reduce
#11198 opened
May 28, 2025 -
Add vectorized_math.h
#11204 opened
May 28, 2025 -
Add optimized_portable_kernels test
#11205 opened
May 28, 2025 -
Add mixed integer precision test for op_mul
#11206 opened
May 28, 2025 -
Qualcomm AI Engine Direct - GA mobilevit
#11208 opened
May 29, 2025 -
NXP backend: Add support for depthwise and separable convolution.
#11215 opened
May 29, 2025 -
check for overflow in calculate_nbytes
#11217 opened
May 29, 2025 -
NOCOMMIT: Bisect CoreML failures when bumping PyTorch pin
#11222 opened
May 29, 2025 -
Export recipes integration in export_llama
#11228 opened
May 29, 2025 -
Expose gen_oplist_lib to clients
#11231 opened
May 29, 2025 -
[ET-VK] De vectorizing sum and moving bias application to the end in conv 2d op to improve performance.
#11235 opened
May 29, 2025 -
[ET-VK] De vectorizing sum and moving bias application to the end in conv 2d op to improve performance.
#11236 opened
May 29, 2025 -
[ET-VK] De vectorizing sum and moving bias application to the end in conv 2d op to improve performance.
#11241 opened
May 29, 2025 -
[ET-VK] De vectorizing sum and moving bias application to the end in conv 2d op to improve performance.
#11242 opened
May 29, 2025 -
Remove outdated editable mode warning from building from source docs
#11245 opened
May 30, 2025 -
Arm backend: Avoid subtraction error on boolean tensors in error diff logging
#11249 opened
May 30, 2025 -
Move c10::DeviceType to a standalone header file
#11250 opened
May 30, 2025 -
Allow us to print output metadata for the case where output is not tensor
#11263 opened
May 30, 2025 -
fix and link
#11267 opened
May 30, 2025 -
Added docs for setting up executorch on windows
#11273 opened
May 30, 2025 -
Improve torch.ops typing
#11276 opened
Jun 2, 2025 -
Add where layer to ops registry
#11277 opened
Jun 2, 2025 -
Arm backend: Remove special host build of flatcc
#11278 opened
Jun 2, 2025 -
Qualcomm AI Engine Direct - GA MobileVit V2
#11279 opened
Jun 2, 2025 -
[RFC] Fetch gflags dynamically
#11285 opened
Jun 2, 2025 -
Milestone2.1
#11286 opened
Jun 2, 2025 -
[1/N] Add backend option
#11288 opened
Jun 2, 2025 -
Use GraphBuilder in memory passes unit tests. # 2
#11292 opened
Jun 2, 2025 -
Use `__cpp_aligned_new` instead of hand-rolling the implementation
#11293 opened
Jun 2, 2025 -
Make op_glu_test input asymmetric
#11294 opened
Jun 2, 2025 -
Implement GLU using internal views to avoid copying
#11295 opened
Jun 2, 2025 -
Create decompose_ops.py and test_decompose_ops.py
#11299 opened
Jun 2, 2025 -
[WIP] Device telemetry for benchmark
#11301 opened
Jun 2, 2025 -
[ET-VK] Use push constants for image and buffer to nchw prepack nodes.
#11305 opened
Jun 3, 2025 -
[ET-VK] Using push constants for convolution prepack dispatches.
#11306 opened
Jun 3, 2025 -
[Draft] Qualcomm AI Engine Direct - Unexpected graph for mutable buffer after export during Quantization
#11309 opened
Jun 3, 2025 -
Arm backend: Support for dynamic shapes and fix resize bugs
#11310 opened
Jun 3, 2025 -
Milestone2.2
#11316 opened
Jun 3, 2025 -
Bump PyTorch pin to dev20250602
#11318 opened
Jun 3, 2025 -
Make exec_aten::optional and string_view direct aliases for std versions
#11321 opened
Jun 3, 2025 -
Reduce memory requirement on export_llama tests with no params (#11175)
#11339 opened
Jun 3, 2025 -
[llm] Add a generic text only LLM runner
#11342 opened
Jun 3, 2025 -
[llm] Add a generic text only LLM runner
#11343 opened
Jun 3, 2025 -
Use GraphBuilder in test_replace_ops_passes. #1
#11344 opened
Jun 3, 2025 -
[ET-VK] Consolidate shader compilation into one vkCreateComputePipelines call
#11345 opened
Jun 3, 2025 -
Save 16 KiB by moving part of optimized add/sub to .cpp
#11346 opened
Jun 3, 2025 -
[ET-VK] Allow clients to specify cache_data_path
#11350 opened
Jun 4, 2025 -
Replace fixed number cmake --build -j in sh and docs #10887
#11351 opened
Jun 4, 2025 -
Switch fbcode builds of ExecuTorch and PyTorch to fbsource sleef
#11352 opened
Jun 4, 2025 -
Qualcomm AI Engine Direct - GA Model Enablement (Roberta)
#11354 opened
Jun 4, 2025 -
Arm backend: Replace asserts with exceptions in quantization annotator
#11356 opened
Jun 4, 2025 -
Qualcomm AI Engine Direct - CI for Non-LLM GA model Part1
#11357 opened
Jun 4, 2025
14 Issues closed by 8 people
-
Don't Serialize Scales/ZP in Flatbuffer
#9029 closed
Jun 3, 2025 -
Mechanism to detect performance CPU core is not reliable
#10549 closed
Jun 3, 2025 -
Move codegen from using `torchgen` to `executorch.codegen`
#11232 closed
Jun 3, 2025 -
Remove available branching for macOS <12
#11259 closed
Jun 2, 2025 -
Remove the option to choose pybindings in install_executorch
#11176 closed
May 30, 2025 -
[torchao] Migrate exact copy of PT2E from torch.ao to torchao
#9856 closed
May 29, 202 8000 5 -
[torchao] Move Int8DynamicActivationIntxWeightConfig out of torchao/experimental.
#9516 closed
May 29, 2025 -
[XNNPACK] partitioner recognizes new torchao quant primitives
#9855 closed
May 29, 2025 -
[QNN] partitioner recognizes new torchao quant primitives
#9854 closed
May 29, 2025 -
torch._dynamo.exc.Unsupported: Attempted to call function marked as skipped
#11128 closed
May 29, 2025 -
Add `extension.BundledModule` to Wrap `extension.Module` with Bundled Program Logic
#10375 closed
May 28, 2025 -
[Build Presets] Create foundation and default configurations
#10716 closed
May 28, 2025 -
Support CoreML export on Linux
#9800 closed
May 28, 2025 -
Missing out variants: {'torchao::dequantize_affine'}
#10663 closed
May 28, 2025
32 Issues opened by 11 people
-
PT2E Dynamic Quantization with XNNPACK Backend for Android fails Loading of method forward in runtime
#11355 opened
Jun 4, 2025 -
x86_64 emulator Tests failing
#11341 opened
Jun 3, 2025 -
Implement portable kernel: native_layer_norm_backward.out
#11337 opened
Jun 3, 2025 -
Implement portable kernel: native_group_norm_backward.out
#11336 opened
Jun 3, 2025 -
Implement portable kernel: embedding_dense_backward.out
#11335 opened
Jun 3, 2025 -
Implement portable kernel: avg_pool2d_backward.grad_input
#11334 opened
Jun 3, 2025 -
Implement portable kernel: _adaptive_avg_pool2d_backward.out
#11333 opened
Jun 3, 2025 -
Implement portable kernel: _fft_r2c.out
#11332 opened
Jun 3, 2025 -
Implement portable kernel: sort.values
#11331 opened
Jun 3, 2025 -
Implement portable kernel: scatter_reduce.two_out
#11330 opened
Jun 3, 2025 -
Implement portable kernel: max_pool3d_with_indices.out
#11329 opened
Jun 3, 2025 -
Implement portable kernel: grid_sampler_2d.out
#11328 opened
Jun 3, 2025 -
Implement portable kernel: col2im.out
#11327 opened
Jun 3, 2025 -
Implement portable kernel: avg_pool3d.out
#11326 opened
Jun 3, 2025 -
Implement portable kernel: avg_pool1d.out
#11325 opened
Jun 3, 2025 -
Implement portable kernel: adaptive_avg_pool1d.out
#11324 opened
Jun 3, 2025 -
Implement portable kernel: _embedding_bag.out
#11323 opened
Jun 3, 2025 -
Implement portable kernel: _adaptive_avg_pool3d.out
#11322 opened
Jun 3, 2025 -
Portable Library: Core-ATen op coverage
#11320 opened
Jun 3, 2025 -
Implement portable kernel: _adaptive_avg_pool2d.out
#11319 opened
Jun 3, 2025 -
High-level api for canned user experience on devtool
#11313 opened
Jun 3, 2025 -
Running Qwen3 in Android LlamaDemo App shows an error while loading tokenizer
#11311 opened
Jun 3, 2025 -
Complie issue cause lost #include
#11307 opened
Jun 3, 2025 -
Migrate Pybindings to Module API
#11297 opened
Jun 2, 2025 -
Cmake selective build: add wrapper for the three APIs.
#11296 opened
Jun 2, 2025 -
torchao build fails on macOS arm64 due to missing symbol c10::StorageImpl::throw_data_ptr_access_error()
#11283 opened
Jun 2, 2025 -
Include Xcode in our macOS runners
#11272 opened
May 30, 2025 -
Remove the outdated warning in building from source documentation
#11229 opened
May 29, 2025 -
Test exported models in Python
#11225 opened
May 29, 2025 -
Manual kernel registration to include library names in API
#11221 opened
May 29, 2025 -
Qwen3-0.6B QNN Execute Error
#11213 opened
May 29, 2025 -
Include ClangCL toolset in MSVC
#11199 opened
May 28, 2025
61 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
support channels last inputs in xnnpack
#11118 commented on
Jun 3, 2025 • 9 new comments -
Add new export LLM config
#11028 commented on
Jun 4, 2025 • 7 new comments -
[Example] Yolo12 Detection sample with OpenVINO/XNNPACK backend
#10156 commented on
Jun 3, 2025 • 6 new comments -
Introduce PAL function table
#10675 commented on
Jun 3, 2025 • 4 new comments -
Qualcomm AI Engine Direct - GA FocalNet
#11097 commented on
Jun 2, 2025 • 2 new comments -
Qualcomm AI Engine Direct - Enable custom operator
#8726 commented on
Jun 4, 2025 • 2 new comments -
Add vectorization in elementwise_util
#9432 commented on
Jun 2, 2025 • 1 new comment -
Implement unary_ufunc functions using elementwise_util
#9386 commented on
May 30, 2025 • 1 new comment -
GA models benchmark script
#11039 commented on
May 31, 2025 • 1 new comment -
Qualcomm AI Engine Direct - QAIRT Visualizer Engagement
#10873 commented on
May 29, 2025 • 0 new comments -
Add aot example with Neutron Backend
#10871 commented on
Jun 3, 2025 • 0 new comments -
Adding operators: bitwiseand, bitwiseor, bitwisexor, embedding, eq, fmod, ge, gt, hardtanh, le, lt, maskedfill, ne, select_copy and quantisedmatmul
#10840 commented on
May 31, 2025 • 0 new comments -
Update MemoryPlanning Verifier to only assume model has user input if it has at least one tensor input
#10617 commented on
May 28, 2025 • 0 new comments -
Qualcomm AI Engine Direct - Streaming Mimi Enablement
#10570 commented on
Jun 2, 2025 • 0 new comments -
Introducing NXP Neutron runtime
#10563 commented on
Jun 3, 2025 • 0 new comments -
Use std::string_view and std::optional
#10541 commented on
Jun 3, 2025 • 0 new comments -
[#9971] Gracefully error out in ETDump part 3 for *profiling_delegate
#10147 commented on
May 29, 2025 • 0 new comments -
Add coreml recipes
#10037 commented on
May 31, 2025 • 0 new comments -
[pytorch hash update] update the pinned pytorch hash
#10955 commented on
Jun 4, 2025 • 0 new comments -
Add torchao kernels to xcframework
#10963 commented on
May 30, 2025 • 0 new comments -
Introduce hydra framework with backwards compatibility
#11029 commented on
Jun 4, 2025 • 0 new comments -
Qualcomm AI Engine Direct - GA CvT
#11036 commented on
Jun 3, 2025 • 0 new comments -
Move get_quantizer_and_quant_params to quantizer_lib
#11056 commented on
May 31, 2025 • 0 new comments -
Convert args to LlmConfig
#11081 commented on
Jun 4, 2025 • 0 new comments -
Qualcomm AI Engine Direct - GA DIT
#11093 commented on
Jun 2, 2025 • 0 new comments -
Use GraphBuilder in reorder unit tests.
#11120 commented on
May 28, 2025 • 0 new comments -
Support more open-source models
#11125 commented on
Jun 4, 2025 • 0 new comments -
Add new dependency library for vulkan tests
#11131 commented on
May 29, 2025 • 0 new comments -
[ET-VK][Ops] aten.tan.default in unary_ops
#11153 commented on
Jun 4, 2025 • 0 new comments -
Enforce clang for Windows builds
#11159 commented on
Jun 3, 2025 • 0 new comments -
Use llm_config instead of args in export_llama functions
#11162 commented on
Jun 4, 2025 • 0 new comments -
adjust platform compatibility for qnn backend
#11179 commented on
May 29, 2025 • 0 new comments -
Benchmark: Fix metrics high variability from run-to-run
#8603 commented on
May 28, 2025 • 0 new comments -
Add timestamps for pte generation in CI
#10761 commented on
May 29, 2025 • 0 new comments -
Build pip wheel and validate AOT workflow on different backends & host environments in CI
#9019 commented on
May 30, 2025 • 0 new comments -
[QCOM] [Llama] Gibberish Result on Llama 3.2 1B
#10900 commented on
May 30, 2025 • 0 new comments -
Format CMakeLists.txt
#10736 commented on
May 30, 2025 • 0 new comments -
No module named 'pytorch_tokenizers'
#11180 commented on
Jun 2, 2025 • 0 new comments -
Consolidate executor_runners
#10819 commented on
Jun 2, 2025 • 0 new comments -
Get rid of fixed number cmake --build -j in sh and docs
#10887 commented on
Jun 4, 2025 • 0 new comments -
[MediaTek] mtk_neuron compile error: 3D permutation not support
#9733 commented on
Jun 4, 2025 • 0 new comments -
NMS op implementation for ExecuTorch in portable mode
#2787 commented on
May 31, 2025 • 0 new comments -
Add allocate tensor util that uses temp allocator
#6090 commented on
May 31, 2025 • 0 new comments -
Redirect stdout and stderr from C++ stream to Python stream
#6390 commented on
May 31, 2025 • 0 new comments -
Changes to sdpa and attention module to support vision encoder attent…
#7350 commented on
May 31, 2025 • 0 new comments -
Changes to SDPA to support no kv cache export
#7530 commented on
May 31, 2025 • 0 new comments -
Add utils to replace torchtune SDPA with ET Custom SDPA
#7531 commented on
May 31, 2025 • 0 new comments -
Add test case to export, quantize and lower vision encoder model for ET
#7532 commented on
May 31, 2025 • 0 new comments -
fix spec_prop_pass
#7974 commented on
Jun 3, 2025 • 0 new comments -
Fix comment in memory_planning.py
#8010 commented on
Jun 3, 2025 • 0 new comments -
remove the exec_aten namespace
#8018 commented on
Jun 3, 2025 • 0 new comments -
Revert to use mean_out than mean_dim_out
#8021 commented on
Jun 3, 2025 • 0 new comments -
[docs][ez] Fix doc build workflow
#8079 commented on
Jun 3, 2025 • 0 new comments -
Adjust tolerance for quantized XNN conv1d tests
#8093 commented on
Jun 3, 2025 • 0 new comments -
[devtool] create stream_data_sink
#8604 commented on
Jun 3, 2025 • 0 new comments -
Neuron buffer allocator decouple from ExecuTorch framework
#8760 commented on
Jun 3, 2025 • 0 new comments -
Adding new memory plannig algorithm heap_optimized_greedy
#8773 commented on
May 31, 2025 • 0 new comments -
Add SupportedTensorDtypes::BOOL
#9584 commented on
May 30, 2025 • 0 new comments -
relax tolerances for all unary float ops
#9585 commented on
May 30, 2025 • 0 new comments -
Add some basic xnnpack recipes
#10035 commented on
May 31, 2025 • 0 new comments -
Adding qualcomm recipes
#10036 commented on
May 31, 2025 • 0 new comments