pytorch/TensorRT
View on GitHubPyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
- Stars
- 3k
- Forks
- 410
- Open beginner issues
- 0
- Indexed issues
- 231
- Avg merge
- 3d 18h
- Merged PRs (30d)
- 78
- Dominant language
- Python
- License
- BSD-3-Clause
- Last GitHub push
- Sep 17, 2026
- Latest indexed
- Sep 19, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- Code of conduct
- Beginner labels
- No beginner labels indexed
231 open issues indexed
Loading issues
-
feature request story: Documentation & Examples
-
bug story: Performance & Benchmarking
Difficulty 5/5 Over a week Newbie friendliness 15/100
-
Story story: CI/CD & Testing Infrastructure
-
bug story: CI/CD & Testing Infrastructure
-
feature request Story: Runtime & Memory & Serialization
-
bug story: LLM & Generative AI
Difficulty 4/5 3-5 days Newbie friendliness 45/100
-
feature request Story: Runtime & Memory & Serialization
-
bug story: Dynamic Shapes & Symbolic Tracing
-
bug story: Dynamic Shapes & Symbolic Tracing
-
bug story: Dynamic Shapes & Symbolic Tracing
-
bug Story: Runtime & Memory & Serialization
-
bug story: Dynamic Shapes & Symbolic Tracing
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
feature request story: LLM & Generative AI
-
feature request Story: Multi-GPU & Distributed & Custom Ops
-
Story Story: Multi-GPU & Distributed & Custom Ops
-
feature request story: TRT-RTX Platform
-
feature request story: LLM & Generative AI
-
feature request story: Performance & Benchmarking
-
feature request Story: Multi-GPU & Distributed & Custom Ops
-
feature request story: Quantization & Precision
-
feature request Story: Multi-GPU & Distributed & Custom Ops
-
Story Story: Multi-GPU & Distributed & Custom Ops
-
story: Dynamo Frontend & Partitioning
-
feature request Story: Runtime & Memory & Serialization
-
feature request story: Dynamo Frontend & Partitioning
-
Story story: CI/CD & Testing Infrastructure
-
Story story: Quantization & Precision
-
Convert torch.cond Openfeature request story: Dynamo Frontend & Partitioning
-
Story story: LLM & Generative AI
-
Story story: LLM & Generative AI
-
Story story: LLM & Generative AI
-
Story story: LLM & Generative AI
-
feature request story: Dynamo Frontend & Partitioning
-
feature request story: Dynamo Frontend & Partitioning
-
Removing ptq.h OpenStory: Build & Install & Packaging
Difficulty 1/5 Under an hour Newbie friendliness 65/100
-
feature request Story: Runtime & Memory & Serialization
-
Story Story: Runtime & Memory & Serialization
-
bug story: Documentation & Examples
Difficulty 3/5 1-2 days Newbie friendliness 45/100
-
bug story: Operator Coverage & Converters
Difficulty 3/5 1-2 days Newbie friendliness 42/100
-
feature request story: LLM & Generative AI
-
bug story: Dynamic Shapes & Symbolic Tracing
-
bug story: TRT-RTX Platform
-
bug Story: Multi-GPU & Distributed & Custom Ops
-
bug story: CI/CD & Testing Infrastructure
-
bug story: CI/CD & Testing Infrastructure
-
bug story: CI/CD & Testing Infrastructure
-
story: Documentation & Examples
-
🐛 [Bug] nn.MultiheadAttention fails with Torch-TensorRT due to non-contiguous tensor before view() Openbug story: LLM & Generative AI
-
bug Story: Runtime & Memory & Serialization
Difficulty 4/5 3-5 days Newbie friendliness 25/100
-
Story story: Documentation & Examples
Difficulty 4/5 3-5 days Newbie friendliness 25/100