-
Notifications
You must be signed in to change notification settings - Fork 596
Insights: pytorch/executorch
Overview
Could not load contribution data
Please try again later
122 Pull requests merged by 39 people
-
Arm backend: Add support for per-channel quantization
#11752 merged
Jun 17, 2025 -
Arm backend: Added decomposition for MaxPool2d with dilation > 0.
#11724 merged
Jun 17, 2025 -
[llm] Add generate_from_pos API to LLM runner
#11570 merged
Jun 17, 2025 -
Add function for input preprocessing in numerical comparator
#11739 merged
Jun 17, 2025 -
Update documents for buffer allocator
#11467 merged
Jun 17, 2025 -
Fix for overriding installed executorch when running optimum-et models
#11745 merged
Jun 17, 2025 -
Fixed linter
#11742 merged
Jun 16, 2025 -
Implement ReplaceMulTensorWithMulAndFullOpsPass.
#11577 merged
Jun 16, 2025 -
Update CMakeLists.txt for extension/apple to strip debug symbols path
#11659 merged
Jun 16, 2025 -
Revert vulkan changes from D76646172 fixup patch
#11727 merged
Jun 16, 2025 -
Fix channels_last_tagged_reshape_pass to handle mixed memory format tuple outputs
#11647 merged
Jun 16, 2025 -
Added evaluation script for qualcomm LlamaModel
#11663 merged
Jun 16, 2025 -
Qualcomm AI Engine Direct - GA Model Enablement (Roberta)
#11354 merged
Jun 16, 2025 -
Qualcomm AI Engine Direct - Enable Lookahead Decoding
#11437 merged
Jun 16, 2025 -
Fix lint
#11728 merged
Jun 16, 2025 -
Install examples and domain libraries as last (optional) step
#11653 merged
Jun 16, 2025 -
Define ET_HAS_EXCEPTIONS macro
#11664 merged
Jun 16, 2025 -
lintrunner init can fail, don't suppress stderr
#11667 merged
Jun 16, 2025 -
Support for cmdline flag to toggle Debug vs Release build types in cmake
#11662 merged
Jun 16, 2025 -
Remove buck-out on clean ET install
#11641 merged
Jun 16, 2025 -
Add et_dump related API to module
#9284 merged
Jun 14, 2025 -
[ET-VK][Ops] choose_qparams_per_token_asymmetric.default test setup
#11556 merged
Jun 14, 2025 -
[ET-VK][Ops] choose_qparams.tensor test setup
#11555 merged
Jun 14, 2025 -
[ET-VK][Ops] choose_qparams ops skeleton test framework
#11554 merged
Jun 14, 2025 -
[ET-VK][Ops] dequantize_per_token.default test setup
#11482 merged
Jun 14, 2025 -
[ET-VK][Ops] dequantize_per_tensor.default test setup
#11481 merged
Jun 14, 2025 -
[ET-VK][Ops] dequantize ops skeleton test framework
#11480 merged
Jun 14, 2025 -
[ET-VK][Ops] quantize_per_tensor.default test setup
#11368 merged
Jun 14, 2025 -
[ET-VK][Ops] quantize_per_token.default test setup
#11367 merged
Jun 14, 2025 -
[ET-VK][Ops] quantize ops skeleton test framework
#11366 merged
Jun 14, 2025 -
[ET-VK][Ops] common test utils for converting aten types to vulkan types
#11575 merged
Jun 14, 2025 -
[ET-VK] double, short, and uint16 dtype runtime support
#11365 merged
Jun 14, 2025 -
[ET] enabling half dtype output for dequantization and making logic consistent
#11552 merged
Jun 14, 2025 -
[ET] enabling half dtype input for quantization
#11479 merged
Jun 14, 2025 -
Define ET_HAS_EXCEPTIONS macro
#11603 merged
Jun 14, 2025 -
[cadence][aot]Implement mul.Tensor to quant fusion.
#11580 merged
Jun 13, 2025 -
[ET-VK][ez] Allow Vulkan operator tests to run on devserver and Mac
#11652 merged
Jun 13, 2025 -
[ET-VK][ez] Allow Vulkan operator tests to run on devserver and Mac
#11648 merged
Jun 13, 2025 -
Qualcomm AI Engine Direct - Enable custom operator
#8726 merged
Jun 13, 2025 -
Mapping between runtime and aot intermediate outputs
#11624 merged
Jun 13, 2025 -
Fix flags in apple_common.cmake
#11643 merged
Jun 13, 2025 -
[ET-VK][ez] Fix type ambiguity relating to
TextureLimits
class#11646 merged
Jun 13, 2025 -
[ET-VK][ez] Fix type ambiguity relating to
TextureLimits
class#11642 merged
Jun 13, 2025 -
[Exutorch] Add broadcast support for le op
#11635 merged
Jun 13, 2025 -
Use GraphBuilder in test_replace_ops_passes. #3
#11501 merged
Jun 13, 2025 -
revert NXP backend: Enable initial unit tests workflow
#11612 merged
Jun 13, 2025 -
Arm backend: Fix warnings from cppcheck in runtime
#11639 merged
Jun 13, 2025 -
Arm backend: Test and track resnet18 and resnet50 models in CI
#11638 merged
Jun 13, 2025 -
Arm backend: Add embedding.default + index_select
#11636 merged
Jun 13, 2025 -
Arm backend: Add validate_valid_dtype
#11472 merged
Jun 13, 2025 -
fix platform inconsistencies
#11547 merged
Jun 13, 2025 -
[Exutorch] Add broadcast support for le op
#11569 merged
Jun 13, 2025 -
Refine Tensor metadata for Swift.
#11634 merged
Jun 13, 2025 -
Return retained objects from Module constructors.
#11633 merged
Jun 13, 2025 -
Update tutorial-arm-ethos-u.md
#11625 merged
Jun 13, 2025 -
Return retained objects from Value constructors.
#11632 merged
Jun 13, 2025 -
Return retained objects from Tensor constructors.
#11631 merged
Jun 13, 2025 -
Return retained objects from NSError constructors.
#11630 merged
Jun 13, 2025 -
Return retained objects from toNSArray.
#11629 merged
Jun 13, 2025 -
Make Tensor data type a generic arg.
#11628 merged
Jun 13, 2025 -
Support for Header File Generation in DTYPE Selective Build in OSS
#11619 merged
Jun 13, 2025 -
Add valueWithFloat API.
#11627 merged
Jun 13, 2025 -
Don't use tensor shape dynamism when comparing tensors.
#11626 merged
Jun 13, 2025 -
Add API to log errors with a custom description appended.
#11591 merged
Jun 13, 2025 -
Update default models to be benchmarked continuously
#11610 merged
Jun 13, 2025 -
Use PAL table override for pybinding log routing
#11616 merged
Jun 13, 2025 -
Support for Model API for Selective Build in OSS
#11601 merged
Jun 13, 2025 -
[ET-VK] New implementation of
cat
operator#11623 merged
Jun 12, 2025 -
[ET-VK] Use dim order when converting buffer index to tensor index
#11622 merged
Jun 12, 2025 -
[ET-VK] Clean up
vTensor
member variables and exposedim order
UBO and push constant#11621 merged
Jun 12, 2025 -
[ET-VK] New implementation of
cat
operator#11508 merged
Jun 12, 2025 -
[ET-VK] Use dim order when converting buffer index to tensor index
#11600 merged
Jun 12, 2025 -
[ET-VK] Clean up
vTensor
member variables and exposedim order
UBO and push constant#11599 merged
Jun 12, 2025 -
Remove ExecuTorch copy of Vectorized
#11613 merged
Jun 12, 2025 -
Make core aten exception ops modifiable at runtime.
#11497 merged
Jun 12, 2025 -
Fix tests and improve CI
#11614 merged
Jun 12, 2025 -
Fix bug in optimized mul's broadcast handling
#11590 merged
Jun 12, 2025 -
Remove ExecuTorch copy of Vectorized
#7042 merged
Jun 12, 2025 -
Improve performance of _to_dim_order_copy
#11545 merged
Jun 12, 2025 -
Add MediaTek backend CI
#7120 merged
Jun 12, 2025 -
Revert D73564127
#11606 merged
Jun 12, 2025 -
gitignore HF tokenizer file
#11609 merged
Jun 12, 2025 -
update codeowners for Tarun and Martin's leaving
#11608 merged
Jun 12, 2025 -
Remove myself from CODEOWNERS
#11605 merged
Jun 12, 2025 -
Use Memcpy in copy_utils
#11430 merged
Jun 12, 2025 -
Benchmark HF optimum-executorch
#11450 merged
Jun 12, 2025 -
[ExecuTorch][#10447] Extend
PyBundledModule
withextension.BundledModule
#11595 merged
Jun 12, 2025 -
solve duplicate dependency issues to unblock pybinding backend migration
#11594 merged
Jun 12, 2025 -
Arm backend: Step tosa-tools pin
#11598 merged
Jun 12, 2025 -
Update coreml transformer with Rope and RMSNorm original definitions
#11583 merged
Jun 12, 2025 -
[ExecuTorch][#10447] Extend
PyBundledModule
withextension.BundledModule
#11565 merged
Jun 12, 2025 -
solve duplicate dependency issues to unblock pybinding backend migration
#11566 merged
Jun 12, 2025 -
Reapply "Add (and fix) OSS check that et_operator_library dtype_selective_build builds (#9245)"
#11589 merged
Jun 12, 2025 -
Reapply "Add (and fix) OSS check that et_operator_library dtype_selective_build builds (#9245)"
#11573 merged
Jun 12, 2025 -
Merge intermediate output with overlapped debug_handles
#11529 merged
Jun 12, 2025 -
[llm] Fix llama/README.md
#11543 merged
Jun 11, 2025 -
Enable selective build in OSS
#11540 merged
Jun 11, 2025 -
Qualcomm AI Engine Direct - multi-method support in to_edge_transform_and_lower_to_qnn
#11436 merged
Jun 11, 2025 -
Remove empty TARGETS file
#11544 merged
Jun 11, 2025 -
Revert "Add (and fix) OSS check that et_operator_library dtype_select…
#11571 merged
Jun 11, 2025 -
Use std::string_view and std::optional
#10541 merged
Jun 11, 2025 -
Add (and fix) OSS check that et_operator_library dtype_selective_build builds
#9245 merged
Jun 11, 2025 -
Revert "Milestone3.1: Support tanh op in XNNPACK backend (#11364)"
#11535 merged
Jun 11, 2025 -
Ability to set external instance + devices
#11393 merged
Jun 11, 2025 -
Create a README for build presets
#11548 merged
Jun 11, 2025 -
Fix mps example for non-LLMs
#11538 merged
Jun 11, 2025 -
Reapply #11294 and #11295 (improve GLU test and implement using internal views to avoid copying)
#11539 merged
Jun 11, 2025 -
Reapply #11294 and #11295 (improve GLU test and implement using internal views to avoid copying)
#11509 merged
Jun 10, 2025 -
Revert vectorization stack
#11536 merged
Jun 10, 2025 -
Back out "Tests failing for exp op in xnnpack"
#11525 merged
Jun 10, 2025 -
Fix flags in apple_common.cmake
#11516 merged
Jun 10, 2025 -
Update tutorial-arm-ethos-u.md
#11531 merged
Jun 10, 2025 -
Updated list of supported chipsets for Qualcomm AI Engine backend
#11453 merged
Jun 10, 2025 -
Gather intermediate output from Events
#11454 merged
Jun 10, 2025 -
Fix missing import during build
#11515 merged
Jun 10, 2025 -
[xnn update prep] Update Dtypes for XNNPACK
#11505 merged
Jun 10, 2025 -
Bump tokenizers
#11510 merged
Jun 10, 2025 -
Arm backend: Bump cortex-m size test threshold
#11520 merged
Jun 10, 2025 -
Configure conflicting ARM baremetal cmake flags
#11493 merged
Jun 10, 2025 -
Use llm_config instead of args in export_llama functions
#11514 merged
Jun 10, 2025 -
Convert args to LlmConfig
#11513 merged
Jun 10, 2025
51 Pull requests opened by 28 people
-
Replace debug handle with `from_node` to trace operator transformation
#11532 opened
Jun 10, 2025 -
[6/N] Add update in module
#11533 opened
Jun 10, 2025 -
[7/N] Add sugar syntax for module.update
#11534 opened
Jun 10, 2025 -
Use safe_numerics util from PyTorch
#11537 opened
Jun 10, 2025 -
Qualcomm AI Engine Direct - GA Albert, Bert, Distilbert, Eurobert
#11546 opened
Jun 11, 2025 -
hf llm example
#11549 opened
Jun 11, 2025 -
Use ExternalProject_Add to build tokenizers
#11550 opened
Jun 11, 2025 -
Phi3 runner uses TextLLMRunner
#11551 opened
Jun 11, 2025 -
[ET-VK][Ops] enabling double support for quantization and dequantization ops
#11553 opened
Jun 11, 2025 -
[ET-VK][Ops] choose_qparams op shaders and impl
#11557 opened
Jun 11, 2025 -
braodcast in op_le
#11568 opened
Jun 11, 2025 -
Add coreml eager model compare
#11574 opened
Jun 11, 2025 -
[wip] Add named data map merge
#11578 opened
Jun 11, 2025 -
[wip] Merge ndm and pte_data_map
#11579 opened
Jun 11, 2025 -
[do not land] selective build size test
#11582 opened
Jun 11, 2025 -
[llm] Fix start_pos not being updated in prefill_chunk()
#11592 opened
Jun 12, 2025 -
Refactor XNNPACK tester to extract delegate-independent tester classes
#11596 opened
Jun 12, 2025 -
[llm] Update metadata max_seq_len based on the max range of dynamic shapes
#11611 opened
Jun 12, 2025 -
[do not land] Support for Header File Generation in DTYPE Selective Build in OSS
#11617 opened
Jun 12, 2025 -
[draft] Change macos runner
#11644 opened
Jun 13, 2025 -
[llm] Add sentencepiece tokenizer support to llm runner
#11645 opened
Jun 13, 2025 -
Implement load_into for Mmap Data Loader
#11654 opened
Jun 13, 2025 -
Reapply D74208085: "Switch fbcode builds of ExecuTorch and PyTorch to fbsource sleef (#11261)"
#11657 opened
Jun 13, 2025 -
Enable kleidiAI in llama runner
#11658 opened
Jun 13, 2025 -
Use elementwise_util instead of functional_util in op_neg
#11660 opened
Jun 13, 2025 -
Revert D76405701
#11661 opened
Jun 13, 2025 -
Use wrappers from xnnpack.h for unary and binary ops (#11584)
#11666 opened
Jun 14, 2025 -
Define ET_HAS_EXCEPTIONS macro
#11681 opened
Jun 14, 2025 -
Only support int8 dtype for quant operators
#11685 opened
Jun 14, 2025 -
[WIP] Add unit tests for getting the delegated payload in exir/backend.
#11699 opened
Jun 15, 2025 -
Implement load_into for SharedPtrDataLoader and add test (#11562)
#11707 opened
Jun 15, 2025 -
[Quantized DeConv Support] Enable Quantized Transposed Convs with groups==1
#11730 opened
Jun 16, 2025 -
[Quantized DeConv Support] Dynamically Quantized Deconvolutions with groups ==1
#11731 opened
Jun 16, 2025 -
[XNNPACK Quantizer] Select between TConvs and Convs
#11732 opened
Jun 16, 2025 -
Use MAP_SHARED to allow sharing memory between processing
#11733 opened
Jun 16, 2025 -
Add script to fetch benchmark results for execuTorch
#11734 opened
Jun 16, 2025 -
deduplicate torch ao debugger tests between pytorch/ao and ExecuTorch
#11735 opened
Jun 16, 2025 -
Revert D76405701
#11736 opened
Jun 16, 2025 -
[ExecuTorch][#10447] Extend `PyBundledModule` with `extension.BundledModule`
#11737 opened
Jun 16, 2025 -
Set pyre-strict for passes unit tests.
#11740 opened
Jun 16, 2025 -
Introduce apply_torch_ops_aten_passes to test mul fusion e2e
#11741 opened
Jun 16, 2025 -
[BE] Add selected custom ops to CI
#11744 opened
Jun 16, 2025 -
Introduce extension/llm/export_llm
#11746 opened
Jun 17, 2025 -
Update PAL override docs for new APIs
#11747 opened
Jun 17, 2025 -
(WIP) Refactor XNN workspace sharing to allow runtime gating
#11748 opened
Jun 17, 2025 -
Fix text_llm_runner unit test
#11750 opened
Jun 17, 2025 -
Add numerical comparator base class and L1 comparator
#11751 opened
Jun 17, 2025 -
Arm backend: Fix bug in decompose linear vector norm
#11755 opened
Jun 17, 2025 -
NXP backend: Enable initial unit tests workflow (#11396)
#11756 opened
Jun 17, 2025
6 Issues closed by 4 people
-
Update MediaTek backend docs using backend template
#8532 closed
Jun 17, 2025 -
Error in Main Activity.java and ModelRunner.java
#11725 closed
Jun 17, 2025 -
[QCOM] Warning when exporting the model
#10281 closed
Jun 12, 2025 -
[Build Presets] Create an android-x86_64 preset
#10721 closed
Jun 11, 2025 -
Complie issue cause lost #include
#11307 closed
Jun 10, 2025 -
Refactor flat_tensor
#10550 closed
Jun 10, 2025
74 Issues opened by 21 people
-
Android native crash when running DeepLabV3Demo with vulkan backend in Android 16
#11754 opened
Jun 17, 2025 -
Failed build of apple-ios example
#11753 opened
Jun 17, 2025 -
Gradle Error while opening the project
#11749 opened
Jun 17, 2025 -
Shared memory for multiple entry points with XNNPACK delegate
#11738 opened
Jun 16, 2025 -
IF i want to build my own executorch lib to deploymodel on cpu, and the api is designed by myself
#11726 opened
Jun 16, 2025 -
torch.split fails in to_edge
#11723 opened
Jun 16, 2025 -
CoreML randn_like fails to lower with internal error
#11722 opened
Jun 16, 2025 -
CoreML randint occasionally generates out of distribution values
#11721 opened
Jun 16, 2025 -
CoreML fails to lower torch.rand
#11720 opened
Jun 16, 2025 -
CoreML model with no inputs fails to load at runtime
#11719 opened
Jun 16, 2025 -
CoreML gives wrong outputs or crashes for torch.diagonal
#11718 opened
Jun 16, 2025 -
CoreML errors out handling torch.linalg.norm with ord="nuc"
#11717 opened
Jun 16, 2025 -
CoreML doesn't handle negative dim values correctly in cumsum
#11716 opened
Jun 16, 2025 -
CoreML argmin/argmax intermittently crashes process
#11715 opened
Jun 16, 2025 -
CoreML floor_divide crashes process
#11714 opened
Jun 16, 2025 -
CoreML fails to lower asinh/acosh
#11712 opened
Jun 16, 2025 -
CoreML missing partitioner constraint for PixelUnshuffle on older targets
#11711 opened
Jun 16, 2025 -
CoreML CircularPad1/2/3d fails to lower
#11710 opened
Jun 15, 2025 -
CoreML ReplicationPad3d fails to load at runtime
#11709 opened
Jun 15, 2025 -
CoreML ReflectionPad3d fails to load at runtime
#11708 opened
Jun 15, 2025 -
CoreML fails to lower maxpool with indices
#11706 opened
Jun 15, 2025 -
CoreML fails to lower ConvTranspose with output padding
#11705 opened
Jun 15, 2025 -
Conv3d with circular padding on portable fails at runtime
#11704 opened
Jun 15, 2025 -
CoreML conv fails to lower with circular padding mode
#11703 opened
Jun 15, 2025 -
CoreML InstanceNorm3d fails to load
#11702 opened
Jun 15, 2025 -
CoreML BatchNorm3d crashes process
#11701 opened
Jun 15, 2025 -
In-place activations alter graph output after lowering
#11700 opened
Jun 15, 2025 -
CoreML missing partitioner constraint for topk with sorted=False
#11698 opened
Jun 14, 2025 -
CoreML missing partitioner constraint for max_pool with dilation
#11697 opened
Jun 14, 2025 -
CoreML fails to lower pooling with single-element padding list
#11696 opened
Jun 14, 2025 -
CoreML missing partitioner constraint for avg_pool2d with a divisor_override
#11695 opened
Jun 14, 2025 -
CoreML missing partition constraint for tensors with rank greater than 5
#11694 opened
Jun 14, 2025 -
CoreML fails to lower integer ReLU
#11693 opened
Jun 14, 2025 -
BF16 relu fails to lower (no delegation)
#11692 opened
Jun 14, 2025 -
CoreML int32 mm with fixed arg fails to load at runtime
#11691 opened
Jun 14, 2025 -
CoreML fails to lower int16 mm with param arg
#11690 opened
Jun 14, 2025 -
CoreML fails to lower addmm with integer alpha/beta parameters
#11689 opened
Jun 14, 2025 -
CoreML crashes when running convolution
#11688 opened
Jun 14, 2025 -
CoreML ignores add/sub alpha parameter
#11687 opened
Jun 14, 2025 -
CoreML partitioner errors out with 8-bit integer types
#11686 opened
Jun 14, 2025 -
XNNPACK sub ignores alpha value
#11684 opened
Jun 14, 2025 -
XNNPACK add ignores alpha value
#11683 opened
Jun 14, 2025 -
Can we use ExecuTorch from cmake-out to export PTEs/PTDs for tests?
#11656 opened
Jun 13, 2025 -
MPS delegate crashes on iOS 26
#11655 opened
Jun 13, 2025 -
Support getting the delegated payload
#11651 opened
Jun 13, 2025 -
Debug discrepancy of `avg_inference_latency` reported from optimum-et models
#11650 opened
Jun 13, 2025 -
Clean up AWS devices
#11649 opened
Jun 13, 2025 -
Android Benchmark App Reports Success Despite Empty Results
#11620 opened
Jun 12, 2025 -
Runtime crash in PreTokenizer when running optimum-et generated gemma3 via llama runner
#11618 opened
Jun 12, 2025 -
Simple indexing prevents ios18.gather from being schedule-able on the ANE
#11615 opened
Jun 12, 2025 -
NDK 28 & Support 16kb page size for Android 15
#11597 opened
Jun 12, 2025 -
Support dim order in Java Tensor
#11593 opened
Jun 12, 2025 -
Deprecate tag implicit qdq pass
#11588 opened
Jun 12, 2025 -
Support Linear Fused Batchnorm
#11587 opened
Jun 12, 2025 -
Support Standalone Batch Norm
#11586 opened
Jun 12, 2025 -
Add dynamism tests for xnnpack model tests
#11585 opened
Jun 12, 2025 -
Move to binary/unary subgraph
#11584 opened
Jun 11, 2025 -
Update Partitioner Dtype Logic
#11581 opened
Jun 11, 2025 -
Add test to ensure scalar_type.fbs remains in sync across the executorch repo
#11572 opened
Jun 11, 2025 -
Add pybindings for program.h/cpp and method.h/cpp
#11567 opened
Jun 11, 2025 -
install_executorch.sh --clean should remove buck-out/
#11564 opened
Jun 11, 2025 -
Implement load_into for the file descriptor data loader
#11563 opened
Jun 11, 2025 -
Implement load_into for the shared_ptr data loader
#11562 opened
Jun 11, 2025 -
Implement load_into for mmap data loader
#11561 opened
Jun 11, 2025 -
Build Windows wheels
#11560 opened
Jun 11, 2025 -
[Build Presets] Update public docs to use build presets
#11559 opened
Jun 11, 2025 -
[Build Presets] Create an ARM Baremetal preset
#11558 opened
Jun 11, 2025 -
Issues during CoreML GA model testing
#11542 opened
Jun 11, 2025 -
CoreML model is crashing on iPhone GPU, but not on iPhone CPU or macOS GPU
#11541 opened
Jun 10, 2025 -
Introduce export_llama to extension/llm as export_llm
#11527 opened
Jun 10, 2025 -
Build runner in cmake in 1 line
#11526 opened
Jun 10, 2025 -
Letting runner support HF cache_positions
#11524 opened
Jun 10, 2025 -
[XNNPACK] Yolo12 model quantization
#11523 opened
Jun 10, 2025
58 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.
-
[1/N] Add BackendOptions class
#11389 commented on
Jun 13, 2025 • 11 new comments -
[3/N] Add update function in backend interface
#11391 commented on
Jun 13, 2025 • 8 new comments -
[4/N] Add backend options map
#11462 commented on
Jun 14, 2025 • 6 new comments -
[xnn update prep] deprecate sdpa
#11506 commented on
Jun 13, 2025 • 4 new comments -
[Example] Yolo12 Detection sample with OpenVINO/XNNPACK backend
#10156 commented on
Jun 10, 2025 • 3 new comments -
NXP backend: Add docker image for nxp backend tests
#11473 commented on
Jun 10, 2025 • 3 new comments -
[5/N] Add update in method
#11463 commented on
Jun 14, 2025 • 3 new comments -
Milestone2.2: Optimize transposes in XNNPACK partition by removing redundant to_copy ops
#11316 commented on
Jun 13, 2025 • 3 new comments -
[ET-VK][Ops] dequantization op shaders and impl
#11483 commented on
Jun 17, 2025 • 2 new comments -
Add aot example with Neutron Backend
#10871 commented on
Jun 11, 2025 • 2 new comments -
Extracting dtype information from model PTE in OSS
#11504 commented on
Jun 12, 2025 • 1 new comment -
Improve torch.ops typing
#11276 commented on
Jun 13, 2025 • 0 new comments -
Don't depend on `aten_headers_for_executorch` when running with HTP simulator since it already gets this dep from xplat
#11260 commented on
Jun 12, 2025 • 0 new comments -
NXP backend: Add support for depthwise and separable convolution.
#11215 commented on
Jun 10, 2025 • 0 new comments -
Enable all platform tests in CMake
#11124 commented on
Jun 13, 2025 • 0 new comments -
[pytorch hash update] update the pinned pytorch hash
#10955 commented on
Jun 17, 2025 • 0 new comments -
Clean up eager quant in llm_export
#10684 commented on
Jun 16, 2025 • 0 new comments -
Update install script and building from source docs
#10652 commented on
Jun 17, 2025 • 0 new comments -
[devtool] create stream_data_sink
#8604 commented on
Jun 16, 2025 • 0 new comments -
Milestone2.1: Partition to_dim_order_copy op in XNN delegate
#11286 commented on
Jun 13, 2025 • 0 new comments -
Device telemetry for benchmark
#11301 commented on
Jun 14, 2025 • 0 new comments -
[Draft] Qualcomm AI Engine Direct - Unexpected graph for mutable buffer after export during Quantization
#11309 commented on
Jun 16, 2025 • 0 new comments -
[ET-VK][Ops] quantization op shaders and impl
#11369 commented on
Jun 17, 2025 • 0 new comments -
[2/N] Add update context
#11390 commented on
Jun 13, 2025 • 0 new comments -
Qualcomm AI Engine Direct - Deprecate convert_bmm_to_matmul pass
#11392 commented on
Jun 13, 2025 • 0 new comments -
Fix typo in native_batch_norm
#11446 commented on
Jun 12, 2025 • 0 new comments -
Automatically determine presets for known platforms
#11461 commented on
Jun 11, 2025 • 0 new comments -
Add legacy mode test
#11492 commented on
Jun 16, 2025 • 0 new comments -
[xnn update prep] Update ET Pthreadpool third-party to google
#11507 commented on
Jun 13, 2025 • 0 new comments -
Unable to run install_executorch.sh on macOS
#11427 commented on
Jun 10, 2025 • 0 new comments -
Build qwen3 with qnn backend fails
#10895 commented on
Jun 11, 2025 • 0 new comments -
Import and extend c10/util/safe_numerics.h
#11370 commented on
Jun 11, 2025 • 0 new comments -
Manual kernel registration to include library names in API
#11221 commented on
Jun 11, 2025 • 0 new comments -
[Build Presets] Create an Android preset
#10720 commented on
Jun 11, 2025 • 0 new comments -
[Build Presets] Create a Windows preset
#10723 commented on
Jun 11, 2025 • 0 new comments -
Clean up turned on flags for pybind preset
#11458 commented on
Jun 11, 2025 • 0 new comments -
Issue with run the Cadence demo on Ubuntu 22.04
#11050 commented on
Jun 11, 2025 • 0 new comments -
Re-inplace slice_copy with slice
#10917 commented on
Jun 11, 2025 • 0 new comments -
Migrate Pybindings to Module API
#11297 commented on
Jun 12, 2025 • 0 new comments -
Fail to allocate temp memory by exporting torch.topk
#8700 commented on
Jun 14, 2025 • 0 new comments -
Optimized add fails fails at runtime with rank error when broadcasting
#10959 commented on
Jun 14, 2025 • 0 new comments -
XNN int8 out of bounds write / invalid outputs
#10960 commented on
Jun 14, 2025 • 0 new comments -
XNN Int8 ReLU gives incorrect outputs
#10961 commented on
Jun 14, 2025 • 0 new comments -
XNN Conv2d won't lower with single stride/dilation/etc.
#10965 commented on
Jun 14, 2025 • 0 new comments -
XNN AvgPool2d fails to lower with single element kernel_size
#10968 commented on
Jun 14, 2025 • 0 new comments -
XNN MaxPool2d fails to lower with single element kernel_size
#10969 commented on
Jun 14, 2025 • 0 new comments -
Successfully registered all kernels from shared library: NOT_SUPPORTED
#8870 commented on
Jun 16, 2025 • 0 new comments -
Multiple Entrypoints and Shared State implementation; Request for comments/feedback.
#8030 commented on
Jun 16, 2025 • 0 new comments -
[v0.7.0] Release Tracker
#11075 commented on
Jun 16, 2025 • 0 new comments -
Export a model with multiple entry points
#7458 commented on
Jun 17, 2025 • 0 new comments -
executorch model Inference time is higher than the torch model
#10297 commented on
Jun 17, 2025 • 0 new comments -
Support higher-order while_loop and scan torch ops
#8769 commented on
Jun 17, 2025 • 0 new comments -
fix spec_prop_pass
#7974 commented on
Jun 16, 2025 • 0 new comments -
Fix comment in memory_planning.py
#8010 commented on
Jun 16, 2025 • 0 new comments -
remove the exec_aten namespace
#8018 commented on
Jun 16, 2025 • 0 new comments -
Revert to use mean_out than mean_dim_out
#8021 commented on
Jun 16, 2025 • 0 new comments -
[docs][ez] Fix doc build workflow
#8079 commented on
Jun 16, 2025 • 0 new comments -
Adjust tolerance for quantized XNN conv1d tests
#8093 commented on
Jun 16, 2025 • 0 new comments