Po-Wei (Vincent) comments

Results 70 comments of


                                            Po-Wei (Vincent)

error when build TensorRT_LLM engine

@zxy1119 any updates after trying https://github.com/NVIDIA/TensorRT-LLM/issues/2124#issuecomment-2308950182?

chore: reference URL refactor

Closing as no activities from requester for +10 days. Feel free to reopen 👍

Error Code 10: Internal Error (Could not find any implementation for node failure of TensorRT 8.5 when running on GPU Jetson Xavier NX

Flatten should be supported in 8.5. @fettahyildizz Can you update the link to the model so we can further investigate?

TensorRT 10 slower than TensorRT 8.6 for models with Instance Normalization layers

Closing due to inactive. Please feel free to reopen!

How to deal with unsupported operations in TensorRT-LLM?

Closing this due to stale. Feel free to reopen

How to use Medusa to support non llama models?

@skyCreateXian any updates on this?

How to use Medusa to support non llama models?

Closing for now. Feel free to reopen after the work is resumed thanks! 👍

Comparison of infer speed between different TRT8.5.3.1 VS TRT 10.5.0.18 on GPU 3060-12G/4060Ti-16G

Hello @gaoyu-cao ! I don't see any onnx models in your provided model link. Can you verify? ![Image](https://github.com/user-attachments/assets/fc507fc0-2adc-4739-8b4a-355a2fc242e2)

Model Performance Degraded when using BFLOAT16 LoRa Adapters

@TheCodeWrangler any updates on this?

How to accelerate GCN using torch-geometric with TensorRT?

Also take a look at https://github.com/pytorch/TensorRT. Closing for now since no response yet but free to reopen the issue!