Skip to content

Issues: pytorch/TensorRT

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

194 Open 1,360 Closed
194 Open 1,360 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

🐛 [Bug] Cuda Runtime (misaligned address) error when REFIT and weight streaming are used together bug Something isn't working
#3305 opened Nov 27, 2024 by zewenli98
@keehyuna
🐛 [Bug] ScatterLayer API Usage Error bug Something isn't working
#3304 opened Nov 25, 2024 by HolyWu
🐛 [Bug] torch._export.serde.serialize.SerializeError: Unsupported list/tuple argument type upon torch_tensorrt.save for ExportedProgram bug Something isn't working
#3303 opened Nov 22, 2024 by fortminors
🐛 [Bug] Could not implicitly convert NumPy data type: i64 to TensorRT bug Something isn't working
#3295 opened Nov 15, 2024 by dudeperf3ct
@apbose
6
✨[Feature] Add pickle_protocol argument for torch_tensorrt.save feature request New feature or request
#3294 opened Nov 14, 2024 by fortminors
@narendasan @peri044
@zewenli98 @lanluo-nvidia
2
✨[Feature] Performance optimization of PyTorch + TRT subgraphs feature request New feature or request
#3277 opened Nov 4, 2024 by keehyuna
1
@keehyuna
✨[Feature] Output buffer optimization in runtime module feature request New feature or request
#3275 opened Nov 4, 2024 by keehyuna
1
@keehyuna
📖 [Story] Optimize the launch overhead of TRT engine and pytorch kernels Story Issues proposing a new Story
#3274 opened Nov 4, 2024 by keehyuna
@keehyuna
❓ [Question] How do you properly deploy a quantized model with tensorrt question Further information is requested
#3267 opened Oct 29, 2024 by Urania880519
@lanluo-nvidia
4
🐛 [Bug] Const indices failed with embedding bag bug Something isn't working
#3263 opened Oct 24, 2024 by sean-xiang-applovin
@zewenli98
1
[Coverage] RuntimeError (torch.ops.aten.expand.default) during matrix multiplication in SwinTransformer block
#3257 opened Oct 22, 2024 by chohk88
🐛 [Bug] Failed to fast refit Llama2-7b with STRIP_PLAN + REFIT bug Something isn't working
#3255 opened Oct 22, 2024 by zewenli98
@zewenli98
2
🐛 [Bug] Encountered bug when using Torch-TensorRT with a pytorch segmentation model bug Something isn't working
#3254 opened Oct 21, 2024 by deo-abhijit
1
Large output differences with facebook/bart-base model
#3252 opened Oct 19, 2024 by chohk88
@chohk88
1
🐛 [Bug] Error when serving Torch-TensorRT JIT model to Nvidia-Triton bug Something isn't working
#3248 opened Oct 18, 2024 by zmy1116
1
6
🐛 [Bug] cannot convert x.to(torch.uint8) bug Something isn't working
#3247 opened Oct 18, 2024 by braindevices
@peri044 @apbose
1
TypeError: 'tensorrt_bindings.tensorrt.ITensor' object is not iterable bug Something isn't working
#3242 opened Oct 15, 2024 by liuzhiyong01
@peri044 @apbose
1
🐛 Check for the casting of the unary operations in conversion/impl/unary/ops.py bug Something isn't working
#3241 opened Oct 15, 2024 by apbose
@apbose
🐛 [Bug] cannot load quantize_fp8 even though the modelopt[all] installed bug Something isn't working
#3232 opened Oct 13, 2024 by braindevices
@lanluo-nvidia
1
🐛 [Bug] torch.ops.aten.remainder.Scalar seems not working with big int bug Something isn't working
#3230 opened Oct 12, 2024 by sean-xiang-applovin
@apbose
3
❓ [Question] How to decide if an Op should support dynamic shape or not question Further information is requested
#3224 opened Oct 9, 2024 by sean-xiang-applovin
15
🐛[chore] Remove type aliases in our codebase bug Something isn't working
#3222 opened Oct 8, 2024 by peri044
@peri044
🐛 [Bug] view_to_reshape metadata mismatch bug Something isn't working
#3221 opened Oct 7, 2024 by sean-xiang-applovin
@peri044
1
🐛 [Bug] _RichMonitor performance regression bug Something isn't working
#3215 opened Oct 6, 2024 by HolyWu
🐛 [Bug] Error: "Conversion of function torch._ops.aten.aten::cumsum not currently supported!" on CUDA 11.8 and 12.1 bug Something isn't working
#3214 opened Oct 6, 2024 by zewenli98
@zewenli98
1
ProTip! Exclude everything labeled bug with -label:bug.