Skip to content

Issues: google-ai-edge/ai-edge-torch

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.

Sign up for GitHub

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

56 Open 71 Closed
56 Open 71 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

how can the ai-edge-torch converter convert the operators supported on edgeTPU devices status:awaiting ai-edge-developer type:feature For feature requests type:performance An issue with performance, primarily inference latency
#450 opened Jan 7, 2025 by JinniPi
@pkgoogle
1
convert error at llama example type:bug Bug
#447 opened Jan 6, 2025 by dlgktjr
@talumbau
2
Pytorch convert to TfLite seems something is wrong, I don't why. status:awaiting ai-edge-developer type:bug Bug
#446 opened Jan 4, 2025 by ZTFtrue
@pkgoogle
6
ReLU6 is not fused properly type:bug Bug
#441 opened Dec 24, 2024 by ilouzl
Facebook media
#439 opened Dec 22, 2024 by Abirhasankas143
1
Llama3.2-1B .task export does not work in mediapipe status:awaiting ai-edge-developer type:support For use-related issues
#411 opened Dec 10, 2024 by mikel-brostrom
@talumbau @pkgoogle
7
Instances of nn.AdaptiveAvgPool2d are always decomposed into primitive floating-point operations status:awaiting ai-edge-developer type:performance An issue with performance, primarily inference latency
#399 opened Nov 29, 2024 by etrommer
@pkgoogle
3
Convolution operator not marked as quantizable when padding is defined in the class instantiation status:contribution welcome type:bug Bug
#398 opened Nov 28, 2024 by etrommer
@pkgoogle
2
InputCellState is incorrectly populated for TFLite model to MLIR conversion using flatbuffer_translate
#397 opened Nov 28, 2024 by gaikwadrahul8
@gaikwadrahul8
2
Looking for selective post training quantization for 8 bit weights and 16 bit activations
#395 opened Nov 28, 2024 by gaikwadrahul8
@gaikwadrahul8
2
Not able to convert OpenAI hugging face TF Whisper model to int8 model status:awaiting ai-edge-developer type:feature For feature requests type:quantization For issues related to quantization
#394 opened Nov 27, 2024 by pkgoogle
@pkgoogle
8
Multiplication following a int8 transposed convolutions isn't constant folded type:bug Bug
#393 opened Nov 27, 2024 by pkgoogle
@gaikwadrahul8
1
error with concatenation when converting QAT model to tflite model using EXPERIMENTAL_TFLITE_BUILTINS_ACTIVATIONS_INT16_WEIGHTS_INT8
#391 opened Nov 27, 2024 by gaikwadrahul8
@gaikwadrahul8
1
Quantization produces large scale coffiecient, which pervents the model from being loaded status:awaiting review Awaiting PR review type:quantization For issues related to quantization
#390 opened Nov 27, 2024 by gaikwadrahul8
@pkgoogle
2
TFLite conversion (w/ int8 quantization) from ConcreteFunction is broken
#389 opened Nov 27, 2024 by gaikwadrahul8
@gaikwadrahul8
1
TFLite Converter, add possibility to ignore some OPs from quantization
#387 opened Nov 27, 2024 by gaikwadrahul8
@gaikwadrahul8
1
SVDF layer implementation compatible with TFLite’s SVDF operator status:awaiting ai-edge-developer type:bug Bug
#386 opened Nov 27, 2024 by gaikwadrahul8
@pkgoogle
2
Re-authoring torch whisper model and convert it to tflite status:awaiting ai-edge-developer type:doc-feature For documentation/documentation update requests type:feature For feature requests
#385 opened Nov 26, 2024 by yangjundy
@pkgoogle
1
TFLite Model used in official documentation doesn't compile on Edge TPU Compiler status:blocked blocked by another issue
#384 opened Nov 26, 2024 by gaikwadrahul8
@pkgoogle
2
TF_SelectV2Op gets legalized to TFL_SelectOp
#383 opened Nov 26, 2024 by gaikwadrahul8
@gaikwadrahul8
1
Is there any plan support onnx model convertting to tflite ? status:awaiting ai-edge-developer type:feature For feature requests
#344 opened Nov 7, 2024 by huanyingjun
@pkgoogle
Converting PyTorch Models to TensorFlow/TFLite with Training Support for Edge Devices status:awaiting ai-edge-developer type:feature For feature requests
#339 opened Nov 5, 2024 by AdwaithAnand
@pkgoogle
1
Custom operator status:awaiting ai-edge-developer type:feature For feature requests
#338 opened Nov 4, 2024 by fiberflow
@pkgoogle
1
Converting the fold operator resulted in an error: Only the Update, Add, Multiply, Maximum, and Minimum operations are currently supported for stablehlo.scatter. Node number 7 (STABLEHLO_SCATTER) failed to prepare status:awaiting ai-edge-developer type:bug Bug
#337 opened Nov 4, 2024 by fiberflow
@pkgoogle
1
torch upsample convert error status:awaiting ai-edge-developer type:bug Bug
#330 opened Oct 30, 2024 by dlgktjr
@pkgoogle
3
ProTip! What’s not been updated in a month: updated:<2024-12-09.