169 Pull requests merged by 40 people

• Qualcomm AI Engine Direct - Ensure that math invariant ops don't change scale and offset

  #11989 merged Jun 29, 2025

• Correct debug handle merging logic

  #12073 merged Jun 29, 2025

• Arm backend: Add VGF tests to add op unit tests

  #12058 merged Jun 28, 2025

• Skip exp float16 test in XNNPACk

  #12097 merged Jun 28, 2025

• Fix llava test target cmake

  #12096 merged Jun 28, 2025

• Introduce TextLLMRunner - sync updates from fbsource

  #12094 merged Jun 28, 2025

• Unbreak build_size_test.sh on Mac

  #12089 merged Jun 28, 2025

• Fix apple frameworks by patching header

  #12092 merged Jun 28, 2025

• Intorduce TextLLMRunner.

  #12055 merged Jun 28, 2025

• [ET][Portable] Test bad alpha values: op_add

  #12091 merged Jun 28, 2025

• [ET][Portable] Test bad alpha values: op_add

  #12030 merged Jun 28, 2025

• Revert "Milestone2.1: Partition to_dim_order_copy op in XNN delegate"

  #12090 merged Jun 28, 2025

• Fix LLaMA demo app.

  #12079 merged Jun 28, 2025

• [ET][Portable] Check scalar overflow: op_leaky_relu

  #12086 merged Jun 28, 2025

• [ET][Portable] Check scalar overflow: op_hardtanh

  #12085 merged Jun 28, 2025

• [ET][Portable] Check scalar overflow: op_scatter

  #12084 merged Jun 28, 2025

• [ET][Portable] Check scalar overflow: op_constant_pad_nd

  #12083 merged Jun 28, 2025

• [ET][Portable] Check scalar overflow: op_scalar_tensor

  #12082 merged Jun 28, 2025

• [ET][Portable] Check scalar overflow: op_full_like

  #12081 merged Jun 28, 2025

• [ET][Portable] Check scalar overflow: op_full

  #12080 merged Jun 28, 2025

• unbreak lintrunner in backends/arm

  #12075 merged Jun 28, 2025

• Detect release builds by comparing CMAKE_BUILD_TYPE to Debug, not Release

  #12045 merged Jun 28, 2025

• Show output of the size command in size test scripts

  #12018 merged Jun 28, 2025

• [ET][Portable] Check scalar overflow: op_leaky_relu

  #12027 merged Jun 27, 2025

• [ET][Portable] Check scalar overflow: op_hardtanh

  #12029 merged Jun 27, 2025

• [ET][Portable] Check scalar overflow: op_scatter

  #12028 merged Jun 27, 2025

• [ET][Portable] Check scalar overflow: op_constant_pad_nd

  #12026 merged Jun 27, 2025

• [ET][Portable] Check scalar overflow: op_scalar_tensor

  #12025 merged Jun 27, 2025

• [ET][Portable] Check scalar overflow: op_full_like

  #12015 merged Jun 27, 2025

• [ET][Portable] Check scalar overflow: op_full

  #12014 merged Jun 27, 2025

• Sync LLaMARunner.h with Meta internal copy

  #12076 merged Jun 27, 2025

• Bump pinned PT commit to 20250625 and mirror torch/standalone to ExecuTorch

  #12068 merged Jun 27, 2025

• Refactor debug_handles type to use DebugHandles type alias

  #12061 merged Jun 27, 2025

• Unbreak build_size_test.sh (-Wvla-cxx-extension) on my local machine

  #12017 merged Jun 27, 2025

• [ET-VK][ez] Handle zero-element tensors when building Vulkan graph

  #12021 merged Jun 27, 2025

• Make hydra and omegaconf core dependency

  #12060 merged Jun 27, 2025

• Fix jni_layer_llama.cpp generate_from_pos missing return

  #12066 merged Jun 27, 2025

• Bump pinned PT commit to 20250625 and mirror torch/standalone to ExecuTorch

  #11968 merged Jun 27, 2025

• Milestone2.1: Partition to_dim_order_copy op in XNN delegate

  #11286 merged Jun 27, 2025

• Arm backend: Print output to log when using BundleIO

  #12000 merged Jun 27, 2025

• [ET-VK][ez] Explicitly skip marking output nodes that are mutable buffers

  #12020 merged Jun 27, 2025

• [llm] Support different shape of input_pos

  #11966 merged Jun 27, 2025

• Fix memory planning algo for blocked mem IDs.

  #11969 merged Jun 27, 2025

• Arm backend: Fix op_index_tensor's ADD accumulator

  #12056 merged Jun 27, 2025

• [diff-train-patch] apply patch to op_fill_test

  #12057 merged Jun 27, 2025

• Use extension/llm directly from LLaMARunner.

  #12050 merged Jun 27, 2025

• Prim ops replace abort with error code

  #11985 merged Jun 27, 2025

• Remove unnecessary validation for local global attention

  #12049 merged Jun 27, 2025

• expose reinplace pass in lowering

  #12044 merged Jun 27, 2025

• Split LLaMA and LLaVA runners.

  #12036 merged Jun 27, 2025

• [ET][Test] Scalar overflow test macro

  #12043 merged Jun 27, 2025

• [ET][Portable] Check scalar overflow: op_fill

  #12042 merged Jun 27, 2025

• [ET][Portable] Add util to check for overflow when casting scalar

  #12041 merged Jun 27, 2025

• [EE/BE][ET][Portable] Eliminate usage of ET_SWITCH_SCALAR_OBJ_TYPES in portable kernels

  #12040 merged Jun 27, 2025

• [ET][Optimized] Eliminate usage of ET_SWITCH_SCALAR in optimized kernels

  #12046 merged Jun 27, 2025

• [EE/BE][ET][Portable] Move scalar_to utils to scalar_utils.h

  #12035 merged Jun 27, 2025

• [ET][Optimized] Eliminate usage of ET_SWITCH_SCALAR in optimized kernels

  #12033 merged Jun 27, 2025

• Benchmark Gemma-3

  #11978 merged Jun 27, 2025

• Pin bump for optimum-executorch

  #12022 merged Jun 27, 2025

• insert write back now tries to avoid inserting if all operations were inplace

  #12008 merged Jun 27, 2025

• [ET][Test] Scalar overflow test macro

  #12013 merged Jun 27, 2025

• [ET][Portable] Check scalar overflow: op_fill

  #12012 merged Jun 27, 2025

• [ET][Portable] Add util to check for overflow when casting scalar

  #12011 merged Jun 27, 2025

• [EE/BE][ET][Portable] Eliminate usage of ET_SWITCH_SCALAR_OBJ_TYPES in portable kernels

  #12010 merged Jun 27, 2025

• Remove obsolete tests from LLaMaRunner.

  #12034 merged Jun 26, 2025

• Move LlmConfig to extension/llm

  #11872 merged Jun 26, 2025

• Support while in pass base

  #12004 merged Jun 26, 2025

• [EE/BE][ET][Portable] Move scalar_to utils to scalar_utils.h

  #12009 merged Jun 26, 2025

• Bump tokenizers to incorporate new features for HF tokenizer

  #11995 merged Jun 26, 2025

• Update MemoryPlanning Verifier to only assume model has user input if it has at least one tensor input

  #10617 merged Jun 26, 2025

• Add idma Fake operators for AoT.

  #11867 merged Jun 26, 2025

• [llm] Route generate_from_pos() JNI API to native llm runner API

  #11952 merged Jun 26, 2025

• Add instructions to enable ccache

  #11838 merged Jun 26, 2025

• Fix mutable buffer tagging in ExecuTorch

  #11990 merged Jun 26, 2025

• Update XNNPACK to CMake Fix

  #11856 merged Jun 26, 2025

• [xnn update prep] Update ET Pthreadpool third-party to google

  #11507 merged Jun 26, 2025

• [xnn update prep] deprecate sdpa

  #11506 merged Jun 26, 2025

• [ET-VK][ez] Handle zero-element tensors when building Vulkan graph

  #11984 merged Jun 26, 2025

• [ET-VK][ez] Explicitly skip marking output nodes that are mutable buffers

  #11983 merged Jun 26, 2025

• Integrated debug_handle to operator name mapping into inspector

  #12001 merged Jun 26, 2025

• Fix pip install . -e when buck2 is not installed

  #11842 merged Jun 26, 2025

• Reapply: "relax tolerances for all unary float ops (#9585)", "Add SupportedTensorDtypes::BOOL (#9584)", new op_mul test (#11206)

  #11976 merged Jun 26, 2025

• NXP backend: Enable initial unit tests workflow (#11396)

  #11756 merged Jun 26, 2025

• Arm backend: Add atan decomposition pass and test

  #11998 merged Jun 26, 2025

• Add functionality to map runtime debug_handles to op names

  #11987 merged Jun 26, 2025

• Fix test_llm_config

  #11977 merged Jun 26, 2025

• Qualcomm AI Engine Direct - support cli

  #11788 merged Jun 26, 2025

• [ET][Portable] Test bad alpha values: op_add

  #11982 merged Jun 26, 2025

• [EE/BE][ET][Portable] Eliminate usage of ET_SWITCH_SCALAR_OBJ_TYPES in portable kernels

  #11981 merged Jun 26, 2025

• [EE/BE][ET][Portable] Move scalar_to utils to scalar_utils.h

  #11980 merged Jun 26, 2025

• Create yaml configs for documented export_llm use cases

  #11938 merged Jun 26, 2025

• Mapping AOT debug_handles to op names

  #11930 merged Jun 26, 2025

• Allow Hydra CLI to override yaml config

  #11926 merged Jun 26, 2025

• Respect selective build for dtype_specialized_elementwise_fn_impl in elementwise_util

  #11975 merged Jun 26, 2025

• Arm backend: Add decomposition for BatchNorm2D no stats

  #11970 merged Jun 25, 2025

• Reinplace.py

  #11918 merged Jun 25, 2025

• Fix typo in native_batch_norm

  #11446 merged Jun 25, 2025

• Implement python deserialize for flat_tensor

  #11779 merged Jun 25, 2025

• Reapply: "relax tolerances for all unary float ops (#9585)", "Add SupportedTensorDtypes::BOOL (#9584)", new op_mul test (#11206)

  #11942 merged Jun 25, 2025

• Use elementwise_util instead of functional_util in op_neg, delete optimized op

  #11660 merged Jun 25, 2025

• [llm] Add arange() tensor maker API

  #11965 merged Jun 25, 2025

• Make scalar_utils more visible

  #11945 merged Jun 25, 2025

• [ET-VK] Allow specifying multiple storage types/memory layouts for an operator + register group norm operator

  #11974 merged Jun 25, 2025

• [ET-VK] Implement `native_group_norm

  #11973 merged Jun 25, 2025

• [ET-VK][testing] Improvement to operator test codegen system

  #11972 merged Jun 25, 2025

• [ET-VK] New Implementation of `permute' operator

  #11971 merged Jun 25, 2025

• Change debug to verbose > 2 for priting raw docments

  #11963 merged Jun 25, 2025

• [ET-VK] Allow specifying multiple storage types/memory layouts for an operator + register group norm operator

  #11828 merged Jun 25, 2025

• [ET-VK] Implement `native_group_norm

  #11827 merged Jun 25, 2025

• [ET-VK][testing] Improvement to operator test codegen system

  #11826 merged Jun 25, 2025

• [ET-VK] New Implementation of `permute' operator

  #11825 merged Jun 25, 2025

• Arm backend: avg_pool2d test not assume availibility of tosa_ref_model

  #11951 merged Jun 25, 2025

• Delete optimized sigmoid

  #11939 merged Jun 25, 2025

• Expose type-erased tensor from generic one.

  #11962 merged Jun 25, 2025

• Arm backend: Add sinh decomposition pass and test

  #11848 merged Jun 25, 2025

• [llm] Support different shape of input_pos

  #11869 merged Jun 25, 2025

• [llm] Add arange() tensor maker API

  #11861 merged Jun 25, 2025

• Arm backend: Add int32 support to aten.mul.Tensor with BI/INT profile

  #11964 merged Jun 25, 2025

• Arm backend: Add support for custom vela.ini

  #11958 merged Jun 25, 2025

• Fix the print

  #11944 merged Jun 25, 2025

• Update LlmConfig preq_mode enums

  #11936 merged Jun 25, 2025

• Init Tensor with an array of scalar by sharing the memory.

  #11948 merged Jun 25, 2025

• Support exp op in XNNPACK backend

  #11803 merged Jun 25, 2025

• Remove is_arvr_mode() from xplat/executorch/runtime/core/portable_type/c10/c10/targets.bzl

  #11830 merged Jun 25, 2025

• Fix bug in le broadcast for single element broadcast

  #11922 merged Jun 25, 2025

• Support analysis along different metrics in the dataset

  #11937 merged Jun 25, 2025

• Make scalar_utils more visible

  #11862 merged Jun 24, 2025

• Update max context length LlmConfig validation

  #11920 merged Jun 24, 2025

• Reland "Implement load_into for Mmap Data Loader"

  #11935 merged Jun 24, 2025

• [5.1/ N] set_option/get_option API with {backend_name, backend options} only

  #11877 merged Jun 24, 2025

• Update README.md

  #11924 merged Jun 24, 2025

• Fix bug in add op to ignore alpha != 1 (fixes: #11683)

  #11777 merged Jun 24, 2025

• Revert mmap loader changes

  #11928 merged Jun 24, 2025

• Move transformer base definition to extension/llm

  #11914 merged Jun 24, 2025

• Update PAL override docs for new APIs

  #11747 merged Jun 24, 2025

• Manual cherry-pick: Re-reapply "Add vectorized_math.h (#11204)", "Add optimized_portable_kernels test (#11205)", and "Add vectorization in elementwise_util (#9432)"

  #11912 merged Jun 24, 2025

• [3/N] Add get_option/set_option function in backend interface

  #11876 merged Jun 24, 2025

• Manual cherry-pick: Enable sleef in xplat_exported_deps of aten_headers_for_executorch

  #11911 merged Jun 24, 2025

• Fix bug in sub op to ignore alpha != 1 (fixes: #11684)

  #11796 merged Jun 24, 2025

• [2/N] Add option context

  #11875 merged Jun 24, 2025

• [1/N] Add BackendOptions class

  #11874 merged Jun 24, 2025

• Arm backend: Adjust pooling input when not divisible by stride

  #11854 merged Jun 24, 2025

• [5.1/ N] set_option/get_option API with {backend_name, backend options} only

  #11865 merged Jun 24, 2025

• [3/N] Add get_option/set_option function in backend interface

  #11391 merged Jun 24, 2025

• [2/N] Add option context

  #11390 merged Jun 24, 2025

• [1/N] Add BackendOptions class

  #11389 merged Jun 24, 2025

• Arm backend: Only fetch what is used

  #11853 merged Jun 24, 2025

• Use export_llm in CI

  #11836 merged Jun 24, 2025

• [XNNPACK Quantizer] Select between TConvs and Convs

  #11776 merged Jun 24, 2025

• Add SNR numerical comparator

  #11859 merged Jun 24, 2025

• Re-reapply "Add vectorized_math.h (#11204)", "Add optimized_portable_kernels test (#11205)", and "Add vectorization in elementwise_util (#9432)"

  #11802 merged Jun 24, 2025

• Add tanh op to XNNPACK backend

  #11804 merged Jun 23, 2025

• Update export_llama in READMEs to use export_llm

  #11811 merged Jun 23, 2025

• Fix LlmConfig enum usage

  #11833 merged Jun 23, 2025

• [Quantized DeConv Support] Enable Quantized Transposed Convs with groups==1

  #11774 merged Jun 23, 2025

• Add inspector numeric gap calculation between AOT and runtime intermediate outputs

  #11855 merged Jun 23, 2025

• Ability to specify full file configs for export_llm

  #11809 merged Jun 23, 2025

• Add script to fetch benchmark results for execuTorch

  #11734 merged Jun 23, 2025

• [Quantized DeConv Support] Dynamically Quantized Deconvolutions with groups ==1

  #11775 merged Jun 23, 2025

• Create a MemoryPlanningAlgo class.

  #11824 merged Jun 23, 2025

• Enable sleef in xplat_exported_deps of aten_headers_for_executorch

  #11801 merged Jun 23, 2025

• Fix shadowing error in mmap_data_loader.cpp

  #11858 merged Jun 23, 2025

• Pull c10 headers directly from PyTorch internally, not from the c10 mirror

  #11835 merged Jun 23, 2025

• Implement load_into for Mmap Data Loader

  #11654 merged Jun 23, 2025

• Arm backend: Add partial support for index.Tensor

  #11851 merged Jun 23, 2025

• Arm backend: Support ScalarType::Bool in EthosUBackend

  #11850 merged Jun 23, 2025

• Arm backend: Add missing bias in pass

  #11847 merged Jun 23, 2025

• Fix apple benchmark app installation issue caused by not installing sentencepiece

  #11834 merged Jun 23, 2025

• Replaced int4 string with torch.int4

  #11845 merged Jun 23, 2025

84 Pull requests opened by 33 people

• pyre-fixmes for D75477355 - executorch

  #11846 opened Jun 23, 2025

• Arm backend: Create ethosu directory

  #11849 opened Jun 23, 2025

• Arm backend: Move Ethos-U backend to generate TOSA-1.0

  #11852 opened Jun 23, 2025

• Added mse range setting

  #11857 opened Jun 23, 2025

• Improve memory planning for submodule hierarchies.

  #11860 opened Jun 23, 2025

• [XNNPACK Quantizer] Select between TConvs and Convs

  #11863 opened Jun 23, 2025

• [Quantized DeConv Support] Dynamically Quantized Deconvolutions with groups ==1

  #11864 opened Jun 23, 2025

• Extend `PyBundledModule` with `extension.BundledModule`

  #11866 opened Jun 24, 2025

• Arm backend: Make per-channel quantization default

  #11873 opened Jun 24, 2025

• Add FACTO operator test skeleton

  #11878 opened Jun 24, 2025

• Add CoreML tester implementation

  #11879 opened Jun 24, 2025

• Add compliance suite skeleton and operator tests

  #11880 opened Jun 24, 2025

• Add tests for activation functions

  #11881 opened Jun 24, 2025

• Add softmax-family tests

  #11882 opened Jun 24, 2025

• Add norm tests

  #11883 opened Jun 24, 2025

• Add convolution tests

  #11884 opened Jun 24, 2025

• Add maxpool/unpool tests

  #11885 opened Jun 24, 2025

• Add avgpool tests

  #11886 opened Jun 24, 2025

• Add adaptive pooling tests

  #11887 opened Jun 24, 2025

• Add reflection and replication pad tests

  #11888 opened Jun 24, 2025

• Add tests for constant and circular padding

  #11889 opened Jun 24, 2025

• Add linear tests

  #11890 opened Jun 24, 2025

• Add embedding tests

  #11891 opened Jun 24, 2025

• Add upsample tests

  #11892 opened Jun 24, 2025

• Add pixel (un)shuffle tests

  #11893 opened Jun 24, 2025

• Add trig function tests

  #11894 opened Jun 24, 2025

• Add tests for more pointwise functions

  #11895 opened Jun 24, 2025

• Add tests for more pointwise ops

  #11896 opened Jun 24, 2025

• Add reduction op tests

  #11897 opened Jun 24, 2025

• Add sort and argsort tests

  #11898 opened Jun 24, 2025

• Add eq and cumsum tests

  #11899 opened Jun 24, 2025

• Add linalg-related tests

  #11900 opened Jun 24, 2025

• Add bmm tests

  #11901 opened Jun 24, 2025

• Add rand-family tests

  #11902 opened Jun 24, 2025

• Add tests for index_put and index_select

  #11903 opened Jun 24, 2025

• Add slice and reshape ops

  #11904 opened Jun 24, 2025

• Add permute, transpose, and masked_fill tests

  #11905 opened Jun 24, 2025

• Add Vulkan tester

  #11906 opened Jun 24, 2025

• Add test runner executable

  #11907 opened Jun 24, 2025

• NXP backend: Improve quantization annotation process

  #11908 opened Jun 24, 2025

• feat: enable adding executorch as a module to zephyr

  #11909 opened Jun 24, 2025

• Move transformer base definition to extension/llm

  #11917 opened Jun 24, 2025

• Arm Zephyr cmake Preset

  #11923 opened Jun 24, 2025

• remove unnecessary print

  #11925 opened Jun 24, 2025

• Expose a method getter api in Module

  #11929 opened Jun 24, 2025

• Split neutron backend test based on executor dependency

  #11934 opened Jun 24, 2025

• Reapply "Implement unary_ufunc functions using elementwise_util (#9386)"

  #11943 opened Jun 24, 2025

• Fix the math in the FuseMulTensorIntoQuantPass.

  #11946 opened Jun 25, 2025

• Add type error suppressions for upcoming upgrade

  #11950 opened Jun 25, 2025

• [Backend Tester] Add FACTO operator test skeleton

  #11953 opened Jun 25, 2025

• Add CoreML tester implementation

  #11954 opened Jun 25, 2025

• Add compliance suite skeleton and operator tests

  #11955 opened Jun 25, 2025

• Add tests for activation functions

  #11956 opened Jun 25, 2025

• Add softmax-family tests

  #11957 opened Jun 25, 2025

• [Backend Tester] Add CoreML tester implementation

  #11959 opened Jun 25, 2025

• [Backend Tester] Add compliance suite skeleton and operator tests

  #11960 opened Jun 25, 2025

• [Backend Tester] Add tests for activation functions

  #11961 opened Jun 25, 2025

• Fix unreachable-break warning in "executorch/runtime/executor/method_meta.cpp"

  #11967 opened Jun 25, 2025

• Benchmark Phi4-mini via optimum

  #11991 opened Jun 26, 2025

• Arm backend: Add VIT test

  #11996 opened Jun 26, 2025

• [et] generate debug handle before opeartor decomposition

  #11997 opened Jun 26, 2025

• [ET-VK][Ops] linear_qta8a_qga4w_qta8o test framework

  #12005 opened Jun 26, 2025

• [ET-VK][Ops] linear_qta8a_qga4w_qta8o impl and shaders

  #12006 opened Jun 26, 2025

• Add Pybindings for Program.h/cpp

  #12016 opened Jun 26, 2025

• Specialize BroadcastIndexesRange for the case where there is only 1 contiguous input

  #12023 opened Jun 26, 2025

• Not depending on examples/models/llama/runner/ APIs

  #12032 opened Jun 26, 2025

• Introduce sym_max and sym_min ops to executorch

  #12037 opened Jun 26, 2025

• Add gtest macros and matchers for Result<T> and Error.

  #12038 opened Jun 26, 2025

• Add llm runner into apple frameworks build

  #12047 opened Jun 27, 2025

• Enable Gemma3 1B on ExecuTorch

  #12048 opened Jun 27, 2025

• Add code to Bundleio to generate error stats

  #12051 opened Jun 27, 2025

• USe -WShadow in clang builds

  #12052 opened Jun 27, 2025

• Qualcomm AI Engine Direct - DRAFT for GA QWEN2.5 0.5B

  #12054 opened Jun 27, 2025

• Fixes in to_executorch for while

  #12062 opened Jun 27, 2025

• Add export recipes for xnnpack (#12069)

  #12070 opened Jun 27, 2025

• fix is_inplace_node check

  #12071 opened Jun 27, 2025

• Pass Dependencies When Proposing Partitions VIA New Group-Based Partitioner

  #12072 opened Jun 27, 2025

• Update test_ring_attention.py to fix CI

  #12074 opened Jun 27, 2025

• Added Command Line Option to Choose Zephyr Toolchain over Arm Bare Metal When Possible

  #12077 opened Jun 27, 2025

• Plumbing for Arm Example Runnner to use Zephyr Toolchain

  #12078 opened Jun 27, 2025

• [wip] Introduce MergedDataMap

  #12087 opened Jun 28, 2025

• [wip] Add MergedDataMap to method

  #12088 opened Jun 28, 2025

• Add `required_for_abi_source_only = True` to extension/android:executorch_llama

  #12093 opened Jun 28, 2025

• Fix the build broken of examples/llm_manual used in llm/getting-started.md

  #12095 opened Jun 28, 2025

27 Issues closed by 12 people

• [CoreML] Quantization example with the mobilenet_v2 does not work

  #12059 closed Jun 29, 2025

• [Benchmark Issue]IPHONE MAX PRO 15 failure investigation [May 22 2025]

  #11083 closed Jun 27, 2025

• Error Code 32 on module.load_method("forward")

  #12053 closed Jun 27, 2025

• Implement load_into for the file descriptor data loader

  #11563 closed Jun 27, 2025

• _load_for_executorch pybinding cannot load model for training

  #4908 closed Jun 27, 2025

• [exir] MemoryPlanning Verifier assumes that if a model has a user input it has at least 1 tensor input.

  #10522 closed Jun 26, 2025

• Add dtype selective build for OSS

  #9983 closed Jun 26, 2025

• Enable selective build model API in OSS

  #11434 closed Jun 26, 2025

• Make PR label checker non-mandatory

  #10864 closed Jun 26, 2025

• [etLLM] New config system to export_llama

  #9449 closed Jun 26, 2025

• x86_64 emulator Tests failing

  #11341 closed Jun 25, 2025

• Fail to export QNN model on SXR2230P SOC

  #8973 closed Jun 25, 2025

• Qwen vocabulary size mismatch when using c++ tokenizer

  #11807 closed Jun 25, 2025

• XNNPACK add ignores alpha value

  #11683 closed Jun 24, 2025

• Dynamism Support in XNNPACK for vision models

  #9008 closed Jun 24, 2025

• Inference Latency + Memory Usage: Proper Dim Order Support

  #9006 closed Jun 24, 2025

• XNNPACK sub ignores alpha value

  #11684 closed Jun 24, 2025

• CoreML CircularPad1/2/3d fails to lower

  #11710 closed Jun 23, 2025

• CoreML missing partitioner constraint for topk with sorted=False

  #11698 closed Jun 23, 2025

• CoreML missing partitioner constraint for avg_pool2d with a divisor_override

  #11695 closed Jun 23, 2025

• CoreML fails to lower torch.rand

  #11720 closed Jun 23, 2025

• CoreML missing partitioner constraint for max_pool with dilation

  #11697 closed Jun 23, 2025

• CoreML fails to lower integer ReLU

  #11693 closed Jun 23, 2025

• CoreML fails to lower int16 mm with param arg

  #11690 closed Jun 23, 2025

• CoreML fails to lower maxpool with indices

  #11706 closed Jun 23, 2025

• CoreML errors out handling torch.linalg.norm with ord="nuc"

  #11717 closed Jun 23, 2025

• Implement load_into for mmap data loader

  #11561 closed Jun 23, 2025

20 Issues opened by 11 people

• Add XNNPack recipes to streamline model transformation pipeline with ExportRecipe

  #12069 opened Jun 27, 2025

• Update documentation for cmake selective build features

  #12065 opened Jun 27, 2025

• [et/devtool] profiling and debugging in one call

  #12064 opened Jun 27, 2025

• [et/devtool] op-level numeric discrepancy detection

  #12063 opened Jun 27, 2025

• [executorch] Add reverse functionalization pass

  #12003 opened Jun 26, 2025

• [extension/llm] IOManager interface

  #12002 opened Jun 26, 2025

• run mtk_build_examples.sh error

  #11999 opened Jun 26, 2025

• sym_max support in ExecuTorch

  #11988 opened Jun 26, 2025

• Unified, Configurable AOT Logging

  #11986 opened Jun 25, 2025

• Improve documentation on running cpp tests in CONTRIBUTING.md

  #11979 opened Jun 25, 2025

• XNNPACK Pin Update

  #11933 opened Jun 24, 2025

• QB4 Packing Kernels in KleidiAI

  #11932 opened Jun 24, 2025

• New SDOT Kernels in KleidiAI

  #11931 opened Jun 24, 2025

• Consolidation of Selective Build APIs for OSS

  #11921 opened Jun 24, 2025

• JNI runner API update

  #11916 opened Jun 24, 2025

• Update Android Executorch example (Image Segmentation) documentation accounting for the newly added feature

  #11915 opened Jun 24, 2025

• Cross Compile Executorch for Arm Cortex M h/w (Raspberry PI Pico 2) and infer a simple model

  #11913 opened Jun 24, 2025

• Implement common backend operator-level tests

  #11910 opened Jun 24, 2025

• Input mutation leaves an extra output in the final execution plan.

  #11870 opened Jun 24, 2025

• Using ExecuTorch on iOS error

  #11868 opened Jun 24, 2025

71 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.

• [5/N] Add get_option/set_option APIs

  #11758 commented on Jun 23, 2025 • 4 new comments

• Milestone2.2: Optimize transposes in XNNPACK partition by removing redundant to_copy ops

  #11316 commented on Jun 28, 2025 • 3 new comments

• Refactor XNN workspace sharing to allow runtime gating

  #11748 commented on Jun 25, 2025 • 3 new comments

• [XNNPACK] Add support for Linear fused BatchNorm

  #11805 commented on Jun 27, 2025 • 2 new comments

• [Example] Yolo12 Detection sample with OpenVINO/XNNPACK backend

  #10156 commented on Jun 28, 2025 • 2 new comments

• [4/N] Add backend options map

  #11462 commented on Jun 23, 2025 • 2 new comments

• Introducing NXP Neutron runtime

  #10563 commented on Jun 27, 2025 • 2 new comments

• Replace debug handle with `from_node` to trace operator transformation

  #11532 commented on Jun 25, 2025 • 2 new comments

• Add torchao kernels to xcframework

  #10963 commented on Jun 29, 2025 • 1 new comment

• Device telemetry for benchmark

  #11301 commented on Jun 25, 2025 • 1 new comment

• GA models benchmark script

  #11039 commented on Jun 27, 2025 • 0 new comments

• [pytorch hash update] update the pinned pytorch hash

  #10955 commented on Jun 29, 2025 • 0 new comments

• Update remove clone to drop no-op q/dq

  #10920 commented on Jun 26, 2025 • 0 new comments

• Buckify quantizer

  #10881 commented on Jun 26, 2025 • 0 new comments

• Clean up eager quant in llm_export

  #10684 commented on Jun 25, 2025 • 0 new comments

• IOManager Interface

  #10418 commented on Jun 24, 2025 • 0 new comments

• Added tensor's dim order ambiguity check

  #10272 commented on Jun 26, 2025 • 0 new comments

• [devtool] create stream_data_sink

  #8604 commented on Jun 27, 2025 • 0 new comments

• Adjust tolerance for quantized XNN conv1d tests

  #8093 commented on Jun 27, 2025 • 0 new comments

• [docs][ez] Fix doc build workflow

  #8079 commented on Jun 27, 2025 • 0 new comments

• Revert to use mean_out than mean_dim_out

  #8021 commented on Jun 27, 2025 • 0 new comments

• Android Benchmark App Reports Success Despite Empty Results

  #11620 commented on Jun 26, 2025 • 0 new comments

• [QD8-BF16-QB4] Update XNNPACK flatbuffer with new XNNPACK Datatypes

  #11164 commented on Jun 25, 2025 • 0 new comments

• Add where layer to ops registry

  #11277 commented on Jun 25, 2025 • 0 new comments

• Qualcomm AI Engine Direct - CI for Non-LLM GA model

  #11357 commented on Jun 27, 2025 • 0 new comments

• Try some QD8-BF16 Experiments

  #11466 commented on Jun 25, 2025 • 0 new comments

• Phi3 runner uses TextLLMRunner

  #11551 commented on Jun 26, 2025 • 0 new comments

• [wip] Add named data map merge

  #11578 commented on Jun 25, 2025 • 0 new comments

• Enable kleidiAI in llama runner

  #11658 commented on Jun 26, 2025 • 0 new comments

• Only support int8 dtype for quant operators

  #11685 commented on Jun 26, 2025 • 0 new comments

• Implement load_into for SharedPtrDataLoader and add test (#11562)

  #11707 commented on Jun 28, 2025 • 0 new comments

• Arm backend: Replace Tensor_Scalar with Tensor_Tensor in sqrt op

  #11783 commented on Jun 23, 2025 • 0 new comments

• NXP backend: Add quantization of aten.view

  #11784 commented on Jun 27, 2025 • 0 new comments

• Bump pinned PT commit to 20250616 and mirror torch/standalone to ExecuTorch

  #11791 commented on Jun 24, 2025 • 0 new comments

• Add last_token_pos in llama_transformer

  #11793 commented on Jun 26, 2025 • 0 new comments

• Install libcpp from release package other than apt-get

  #11832 commented on Jun 23, 2025 • 0 new comments

• Ops with included input dim order conversion fail at runtime

  #11086 commented on Jun 25, 2025 • 0 new comments

• Add dynamism tests for xnnpack model tests

  #11585 commented on Jun 25, 2025 • 0 new comments

• IF i want to build my own executorch lib to deploymodel on cpu, and the api is designed by myself

  #11726 commented on Jun 25, 2025 • 0 new comments

• CoreML model is crashing on iPhone GPU, but not on iPhone CPU or macOS GPU

  #11541 commented on Jun 25, 2025 • 0 new comments

• executorch model Inference time is higher than the torch model

  #10297 commented on Jun 25, 2025 • 0 new comments

• QNN backend Compilation

  #8640 commented on Jun 25, 2025 • 0 new comments

• Refactor binary op partitioner configs under binary op config class

  #9024 commented on Jun 24, 2025 • 0 new comments

• Freeing unpacked weights immediately after packing

  #9013 commented on Jun 24, 2025 • 0 new comments

• Shared activation memory with ExecuTorch

  #9012 commented on Jun 24, 2025 • 0 new comments

• Setup Build-Size Check in CI for XNNPACK Dependency

  #9011 commented on Jun 24, 2025 • 0 new comments

• Binary Size: Selective Build

  #9010 commented on Jun 24, 2025 • 0 new comments

• Increased Op Coverage:

  #9009 commented on Jun 24, 2025 • 0 new comments

• BF16 Support

  #9004 commented on Jun 24, 2025 • 0 new comments

• Hardened FP16 Support

  #9005 commented on Jun 24, 2025 • 0 new comments

• [v0.7.0] Release Tracker

  #11075 commented on Jun 24, 2025 • 0 new comments

• Issue with dynamic_shapes when there are atleast one input argument whose dimensions are not dynamic

  #11820 commented on Jun 24, 2025 • 0 new comments

• Android native crash when running DeepLabV3Demo with vulkan backend in Android 16

  #11754 commented on Jun 23, 2025 • 0 new comments

• remove the exec_aten namespace

  #8018 commented on Jun 27, 2025 • 0 new comments

• Fix comment in memory_planning.py

  #8010 commented on Jun 27, 2025 • 0 new comments

• fix spec_prop_pass

  #7974 commented on Jun 27, 2025 • 0 new comments

• Support higher-order while_loop and scan torch ops

  #8769 commented on Jun 28, 2025 • 0 new comments

• Issues during CoreML GA model testing

  #11542 commented on Jun 27, 2025 • 0 new comments

• Failed build of apple-ios example

  #11753 commented on Jun 27, 2025 • 0 new comments

• Manual kernel registration to include library names in API

  #11221 commented on Jun 27, 2025 • 0 new comments

• Python apis for loading and saving .ptd from dictionaries

  #8542 commented on Jun 27, 2025 • 0 new comments

• torch.split fails in to_edge

  #11723 commented on Jun 27, 2025 • 0 new comments

• Fail to allocate temp memory by exporting torch.topk

  #8700 commented on Jun 27, 2025 • 0 new comments

• Freeing memory using free() which was not allocated by malloc()

  #11395 commented on Jun 27, 2025 • 0 new comments

• Add test to ensure scalar_type.fbs remains in sync across the executorch repo

  #11572 commented on Jun 27, 2025 • 0 new comments

• Multiple Entrypoints and Shared State implementation; Request for comments/feedback.

  #8030 commented on Jun 27, 2025 • 0 new comments

• (release/0.5) ./install_requirements.sh fails due to conflicting dependencies.

  #9307 commented on Jun 27, 2025 • 0 new comments

• Deprecate tag implicit qdq pass

  #11588 commented on Jun 26, 2025 • 0 new comments

• Export and run lora llama3b with adapter weights

  #9580 commented on Jun 26, 2025 • 0 new comments

• Migrate Pybindings to Module API

  #11297 commented on Jun 26, 2025 • 0 new comments

• Shared memory for multiple entry points with XNNPACK delegate

  #11738 commented on Jun 26, 2025 • 0 new comments