-
Notifications
You must be signed in to change notification settings - Fork 469
Issues: pytorch/executorch
Label tracking meta-issue (edit me to get automatically CC'ed...
#7679
opened Jan 15, 2025 by
mergennachin
Open
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
The execution permission of qnn_executor_runner file is removed after the runner file copied to android device.
#9072
opened Mar 9, 2025 by
codereba
updated Mar 9, 2025
ExecuTorch runner of Qnn backend can't run the pte model by following the tutorial.
module: qnn
Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/
module: user experience
Issues related to reducing friction for users
partner: qualcomm
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#8762
opened Feb 27, 2025 by
TheBetterSolution
updated Mar 9, 2025
Successfully registered all kernels from shared library: NOT_SUPPORTED
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#8870
opened Mar 1, 2025 by
ismukhin
updated Mar 8, 2025
[Request Help] I refer the Delegate Debugging document to debug the QLoRA_LLama 3.2-1B model, and want to get the pipeline of linear operation delegation and determine the underlying kernel in XNNPACK
module: devtools
Issues related to developer tools and code under devtools/
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#9034
opened Mar 7, 2025 by
liye0626
updated Mar 7, 2025
Dynamic Parameters for Mediatek Delegate
partner: mediatek
Issues related to the Mediatek delegate
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#9035
opened Mar 7, 2025 by
shreshth-tru
updated Mar 7, 2025
Optimized linear op doesn't support bias
actionable
Items in the backlog waiting for an appropriate impl/fix
enhancement
Not as big of a feature, but technically not a bug. Should be easy to fix
good first issue
Good for newcomers
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#8234
opened Feb 5, 2025 by
swolchok
updated Mar 7, 2025
ConstraintViolationError
module: exir
Issues related to Export IR and the code under exir/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#6782
opened Nov 12, 2024 by
adonnini
updated Mar 7, 2025
Model Load Time: SIMD Packing Kernels for Blockwise Quantization
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Dynamism Support in XNNPACK for vision models
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Inference Latency + Memory Usage: Proper Dim Order Support
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Hardened FP16 Support
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Memory Usage: XNNPACK Weights Cache + Blob Storage Service
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
BF16 Support
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Model File Size: Backend Weight Sharing via. Blob Storage Service
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
[Request Help] “torch._dynamo.exc.UserError: Could not guard on data-dependent expression Eq(u77 - 1, 1)"
module: exir
Issues related to Export IR and the code under exir/
module: user experience
Issues related to reducing friction for users
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#8988
opened Mar 6, 2025 by
liye0626
updated Mar 7, 2025
Increased Op Coverage:
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Binary Size: Selective Build
module: build/install
Issues related to the cmake and buck2 builds, and to installing ExecuTorch
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Setup Build-Size Check in CI for XNNPACK Dependency
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Shared activation memory with ExecuTorch
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Build pip wheel and validate AOT workflow on different backends & host environments in CI
module: build/install
Issues related to the cmake and buck2 builds, and to installing ExecuTorch
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#9019
opened Mar 6, 2025 by
larryliu0820
updated Mar 7, 2025
SDPA custom op works without kv cach
module: llm
Issues related to LLM examples and apps, and to the extensions/llm/ code
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#9014
opened Mar 6, 2025 by
iseeyuan
updated Mar 7, 2025
Freeing unpacked weights immediately after packing
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Support Dynamically Quantized Convolutions
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Duplicate Dynamic Quant Chain in XNNPACK Lowering Flow
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Partitioner to not delegate mixed dtype operators
module: xnnpack
Issues related to xnnpack delegation and the code under backends/xnnpack/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.