-
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
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
[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
Don't Serialize Scales/ZP in Flatbuffer
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
Refactor binary op partitioner configs under binary op config class
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
Quantized MobileBert Model Fails with XNNPACK Assertion Error on Android Deployment
#8994
opened Mar 6, 2025 by
qxuan512
[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
Enable dynamic shapes for torchao:8daXw quant ops
module: examples
Issues related to demos under examples/
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#8981
opened Mar 6, 2025 by
jackzhxng
Previous Next
ProTip!
Exclude everything labeled
bug
with -label:bug.