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

30 Open 41 Closed
30 Open 41 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

Request for tflite full int8 static quantization with calibration dataset status:awaiting ai-edge-developer type:feature For feature requests type:quantization For issues related to quantization
#296 opened Oct 15, 2024 by hayyaw
@pkgoogle
1
Conversion fails on custom models (DCGAN, pix2pix) status:awaiting ai-edge-developer type:bug Bug type:precision/accuracy For issues where the precision/accuracy appear incorrect
#295 opened Oct 11, 2024 by jchwenger
@pkgoogle
2
Error Using Converted Phi-3.5-mini TFLite in Android App status:awaiting ai-edge-developer type:feature For feature requests
#293 opened Oct 11, 2024 by chienhuikuo
@pkgoogle
3
Torch unsqueeze / reshape dimensions not preserved upon TFLite conversion status:awaiting ai-edge-developer type:bug Bug
#288 opened Oct 8, 2024 by gudgud96
@pkgoogle
1
Getting an error while generating quantized tiny llama model due to AI-edge-quantizer status:awaiting user response When awaiting user response status:more data needed This label needs to be added to stale issues and PRs. type:bug Bug
#286 opened Oct 7, 2024 by pallaviNNT
@pkgoogle
2
Unable to convert Qwen2.5 to mediapipe supported format status:awaiting ai-edge-developer type:support For use-related issues
#275 opened Oct 1, 2024 by atultiwari
@talumbau @pkgoogle
7
Converting MaxPool2D with dynamic spatial dimensions crashes status:awaiting ai-edge-developer type:bug Bug
#270 opened Sep 30, 2024 by sc-aharri
@pkgoogle
1
Not able to convert Llama 3.2 1B Instruct to Tflite format status:awaiting ai-edge-developer type:bug Bug
#269 opened Sep 29, 2024 by atultiwari
@pkgoogle
5
Error when exporting a model that uses torch.sum() status:awaiting ai-edge-developer type:bug Bug
#268 opened Sep 29, 2024 by rishi-menon
@pkgoogle
1
Unable to resolve runtime symbol: `xla_mark_tensor'. status:awaiting ai-edge-developer type:bug Bug
#265 opened Sep 27, 2024 by Clod98
@pkgoogle
5
Problems with quantization status:awaiting ai-edge-developer type:bug Bug
#264 opened Sep 27, 2024 by spacycoder
@pkgoogle
1
Trace model in model-explorer status:awaiting user response When awaiting user response type:support For use-related issues
#254 opened Sep 24, 2024 by nigelzzzzzzz
@pkgoogle
8
Replace Int64 with Int32 for edge type:support For use-related issues
#246 opened Sep 21, 2024 by rfechtner
@pkgoogle
4
data_ptr_value % kDefaultTensorAlignment == 0 was not true. status:awaiting ai-edge-developer status:awaiting review Awaiting PR review status:contribution welcome type:bug Bug
#237 opened Sep 18, 2024 by nigelzzzzzzz
@pkgoogle
10
Different with gemma2 / gemma status:awaiting ai-edge-developer type:bug Bug
#236 opened Sep 18, 2024 by nigelzzzzzzz
@talumbau
8
Encountered 'Redefinition of symbol: gelu_decomp_27' issue while converting Qwen2 model to TFLite status:awaiting user response When awaiting user response status:stale type:bug Bug
#235 opened Sep 18, 2024 by tilfdev
@haozha111
6
Conversion fails on model loaded via torch.load or torch.jit.load status:awaiting user response When awaiting user response type:support For use-related issues
#221 opened Sep 13, 2024 by saseptim
@pkgoogle
12
OOM Error in Gemini 2 2B TFLite Conversion with Quantization on 80GB RAM status:awaiting ai-edge-developer type:memory An issue with memory, memory performance, or memory leaks
#192 opened Sep 5, 2024 by KennethanCeyer
@haozha111 @v-dziuba
6
Tiny-llama Encountered unresolved custom op: odml.update_kv_cache type:bug Bug
#175 opened Aug 28, 2024 by vignesh-spericorn
@majiddadashi @haozha111 @hheydary
3
int8 tflite conversion crashes status:awaiting ai-edge-developer type:feature For feature requests
#150 opened Aug 15, 2024 by codewarrior26
@pkgoogle
9
Tensor Shape Mismatch During TFLite Quantization Conversion type:bug Bug
#137 opened Aug 8, 2024 by spacycoder
@paulinesho
6
quant_config Dtype INT16 support request type:feature For feature requests
#136 opened Aug 8, 2024 by ZORO-Q
@paulinesho
text_generator_main.cc using tinyllama model to inference can show Garbled characters status:awaiting ai-edge-developer type:bug Bug
#109 opened Jul 26, 2024 by nigelzzz
@hheydary @pkgoogle
18
Replace SELECT with SELECT_V2 type:bug Bug
#93 opened Jul 17, 2024 by pjpratik
@pkgoogle
3
Converting Torch modules that use the max function status:awaiting review Awaiting PR review type:bug Bug
#81 opened Jul 5, 2024 by hbellafkir
@pkgoogle
3
ProTip! What’s not been updated in a month: updated:<2024-09-16.