pytorch/executorch

View on GitHub

On-device AI across mobile, embedded and edge for PyTorch

Stars: 5k
Forks: 1.2k
Open beginner issues: 0
Indexed issues: 851
Avg merge: 2d 10h
Merged PRs (30d): 581

Dominant language: Python
License: No license data
Last GitHub push: Sep 20, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: good first issue help wanted

Beginner friendly Everything

Open All

851 open issues indexed

Building wheel for executorch (pyproject.toml) did not run successfully. Open

module: build/install triaged

pytorch/executorch#8874 · 17 comments · 2 assignees · Opened Mar 3, 2025
[Request Help] “torch._dynamo.exc.UserError" Open

module: exir module: user experience triaged

pytorch/executorch#8873 · 14 comments · 2 assignees · Opened Mar 3, 2025
Failure to set up Executorch Open

module: user experience need-user-input

pytorch/executorch#8869 · 12 comments · 1 assignee · Opened Mar 1, 2025
Add upstream flatcc option to avoid installing under the source tree Open

actionable module: build/install triaged

pytorch/executorch#8867 · 1 assignee · Opened Mar 1, 2025
Use real image input in demo colab notebook Open

module: examples module: user experience triaged

Difficulty 3/5 1-2 days Newbie friendliness 38/100

pytorch/executorch#8851 · 1 comment · Opened Feb 28, 2025
XnnpackBackend init failed while running export-based quantized pte model using ExecuTorch Runtime Open

module: xnnpack triaged

Difficulty 4/5 3-5 days Newbie friendliness 30/100

pytorch/executorch#8830 · 4 comments · Opened Feb 28, 2025
Request for Support adaptive_instance_normalization for executorch Open

need-user-input

Difficulty 5/5 Over a week Newbie friendliness 25/100

pytorch/executorch#8819 · 1 comment · Opened Feb 28, 2025
Track model pte size in the benchmark dashboard Open

module: benchmark triaged

pytorch/executorch#8810 · 2 assignees · Opened Feb 28, 2025
to_edge_transform_and_lower is broken when backend partitioners request aliased/mutable ops to be preserved Open

module: exir triaged

pytorch/executorch#8781 · 2 comments · 2 assignees · Opened Feb 27, 2025
Add const_prop_pass inside to_edge Open

enhancement module: exir triaged

pytorch/executorch#8774 · 2 comments · 1 reaction · 1 assignee · Opened Feb 27, 2025
Support higher-order while_loop and scan torch ops Open

module: exir module: runtime triaged

Difficulty 5/5 Over a week Newbie friendliness 35/100

pytorch/executorch#8769 · 29 comments · Opened Feb 27, 2025
Support Unbound Dynamic Tensor Memory Open

module: runtime module: user experience triaged

Difficulty 5/5 Over a week Newbie friendliness 25/100

pytorch/executorch#8766 · Opened Feb 27, 2025
Allow overlapping delegate allocations with ET-owned memory Open

module: runtime module: user experience triaged

Difficulty 5/5 Over a week Newbie friendliness 25/100

pytorch/executorch#8764 · 6 comments · Opened Feb 27, 2025
ExecuTorch runner of Qnn backend can't run the pte model by following the tutorial. Open

module: qnn module: user experience partner: qualcomm triaged

pytorch/executorch#8762 · 13 comments · 1 assignee · Opened Feb 27, 2025
Long Prompt || .pte Generation || Mediatek Open

module: llm/evaluation module: mediatek module: user experience partner: mediatek triaged

pytorch/executorch#8725 · 4 comments · 1 reaction · 2 assignees · Opened Feb 26, 2025
[RFC] Canonicalize python file structure Open

enhancement triaged

pytorch/executorch#8699 · 11 comments · 2 reactions · 1 assignee · Opened Feb 25, 2025
Failed to build installable wheels for some pyproject.toml based projects (executorch) Open

module: user experience triaged

pytorch/executorch#8684 · 8 comments · 1 reaction · 1 assignee · Opened Feb 25, 2025
[Android] Error running a transformer decoder-based neural network Open

module: android module: user experience triaged

pytorch/executorch#8665 · 51 comments · 1 assignee · Opened Feb 25, 2025
QNN backend Compilation Open

module: qnn module: runtime partner: qualcomm triaged

pytorch/executorch#8640 · 13 comments · 2 assignees · Opened Feb 23, 2025
Executorch does not seem to be able to accelerate Anomaly Transformer inference Open

module: llm module: user experience

Difficulty 4/5 3-5 days Newbie friendliness 32/100

pytorch/executorch#8631 · 1 comment · Opened Feb 21, 2025
Running model - Missing fileS Open

module: build/install need-user-input triaged

Difficulty 3/5 1-2 days Newbie friendliness 35/100

pytorch/executorch#8619 · 2 comments · Opened Feb 21, 2025
[ET-LLM] Clean up llama/model.py Open

module: llm triaged

pytorch/executorch#8574 · 1 assignee · Opened Feb 19, 2025
Reducing memory footprint of Llama models for Executorch Open

module: llm triaged

pytorch/executorch#8547 · 4 comments · 1 reaction · 1 assignee · Opened Feb 18, 2025
Python apis for loading and saving .ptd from dictionaries Open

good first issue module: training triaged

Difficulty 4/5 3-5 days Newbie friendliness 42/100

pytorch/executorch#8542 · 9 comments · Opened Feb 18, 2025
Symbol undefind error in the to_out_var_pass by inputs with dynamic dims Open

module: user experience module: xnnpack triaged

pytorch/executorch#8539 · 17 comments · 1 reaction · 2 assignees · Opened Feb 18, 2025
Query embeddings using executorch generate API Open

triaged

pytorch/executorch#8517 · 6 comments · 1 assignee · Opened Feb 17, 2025
Add heap based greedy planning algorithm and graph coloring algorithm for memory planning. Open

module: exir triaged

pytorch/executorch#8467 · 2 comments · 1 assignee · Opened Feb 13, 2025
Performance - No constant folding/propagation happens on final .pte Open

module: exir triaged

pytorch/executorch#8446 · 11 comments · 1 reaction · 1 assignee · Opened Feb 13, 2025
CPU Overhead After ANE Execution Open

module: coreml triaged

Difficulty 4/5 3-5 days Newbie friendliness 35/100

pytorch/executorch#8445 · 1 comment · Opened Feb 13, 2025
ANE compile OOMs on certain input shapes Open

module: coreml triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

pytorch/executorch#8439 · 2 comments · Opened Feb 13, 2025
Make export_llm as a separate binary Open

module: examples triaged

pytorch/executorch#8432 · 1 assignee · Opened Feb 12, 2025
[etLLM] KV Cache as IO by default, as attribute optional Open

module: llm triaged

pytorch/executorch#8417 · 1 comment · 1 assignee · Opened Feb 12, 2025
Import torch error for torch==dev20250131 during install of viable/strict branch. Open

module: build/install needs reproduction triaged

pytorch/executorch#8409 · 5 comments · 1 assignee · Opened Feb 12, 2025
we should have a CI job that builds with logging disabled Open

module: build/install triaged

pytorch/executorch#8400 · 1 assignee · Opened Feb 12, 2025
[Android benchmarking] Add support to benchmark individual op Open

module: android module: benchmark triaged

pytorch/executorch#8385 · 1 assignee · Opened Feb 11, 2025
Migrate export_llama to to_edge_transform_and_lower API Open

module: examples triaged

pytorch/executorch#8378 · 1 assignee · Opened Feb 11, 2025
Support Kyutai-labs Moshi and Hibiki models Open

module: llm triaged

Difficulty 5/5 Over a week Newbie friendliness 25/100

pytorch/executorch#8372 · 2 comments · 1 reaction · Opened Feb 11, 2025
[etLLM] Runtime components to support LLM models Open

module: llm triaged

pytorch/executorch#8358 · 1 reaction · 1 assignee · Opened Feb 11, 2025
Compile with -Wint-in-bool-context flag Open

module: runtime triaged

pytorch/executorch#8357 · 2 assignees · Opened Feb 11, 2025
Run critical models & recipes on pull request Open

enhancement module: benchmark module: user experience triaged

pytorch/executorch#8348 · 1 assignee · Opened Feb 10, 2025
Get CI coverage signal for both Python and C++ Open

module: ci triaged

Difficulty 4/5 3-5 days Newbie friendliness 35/100

pytorch/executorch#8347 · Opened Feb 10, 2025
Feature Request: Integrate MarkdownView in Android Demo App for Proper Markdown Rendering Open

module: android triaged

pytorch/executorch#8309 · 2 comments · 1 assignee · Opened Feb 7, 2025
Benchmark Hugging Face models via Optimum integration Open

module: benchmark triaged

pytorch/executorch#8294 · 1 comment · 1 assignee · Opened Feb 6, 2025
Add Vulkan Delegate Benchmarks for Llama 3.2 (1B and 3B) and MobileNet Open

module: benchmark module: vulkan triaged

pytorch/executorch#8293 · 2 reactions · 1 assignee · Opened Feb 6, 2025
Improve common error messages Open

module: user experience triaged

pytorch/executorch#8273 · 2 comments · 1 reaction · 1 assignee · Opened Feb 6, 2025
Prototype benchmarking with private/custom devices that are not leased via AWS Open

module: benchmark module: user experience triaged

pytorch/executorch#8251 · 2 comments · 1 reaction · 1 assignee · Opened Feb 6, 2025
Support benchmark with arbitrary binaries on Android Open

module: benchmark module: user experience triaged

pytorch/executorch#8250 · 1 comment · 1 assignee · Opened Feb 6, 2025
DevX: Track the benchmark infra health and usage Open

enhancement module: benchmark module: user experience triaged

pytorch/executorch#8247 · 8 comments · 1 reaction · 1 assignee · Opened Feb 6, 2025
Support benchmark using prebuilt artifacts Open

module: benchmark module: user experience triaged

pytorch/executorch#8246 · 7 comments · 1 assignee · Opened Feb 6, 2025
Support scheduling benchmark jobs via scripts Open

module: benchmark module: user experience triaged

pytorch/executorch#8245 · 1 comment · 2 assignees · Opened Feb 6, 2025

pytorch/executorch

Get new issues in your inbox