Kanghwan

Closing this issue as stale. If the problem persists in the latest release, please feel free to open a new one. Thank you!

@liquanfeng , Thanks for catching that! Although the code is still present [here](https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/models/llama/convert.py#L641-L649), it appears to be specific to the old TensorRT backend. The PyTorch backend, which is the preferred...

I’m closing this issue due to its prolonged inactivity. I hope the comments above have addressed the questions. If the issue still exists in the latest release, please open a...

@nsealati , Just checking in~, if this issue is no longer relevant, please let me know so we can close it. If it is still affecting you, could you try...

Closing the issue as stale. Please feel free to open a new issue if the problem persists with the latest release. Thank you!

@yubofredwang , I hope you’ve found the information you were looking for, but I’m sharing a more recent one: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tensorrt-llm/containers/release

Due to the issue’s prolonged inactivity, I’m closing it. I hope the comments above have addressed the question. If the problem persists in the latest release, please open a new...

Closing this issue as stale. If this issue is still relevant to you, please try running the model with the latest release. Also, consider switching to PyTorch workflow, which is...

Apologies for the delayed response. The Qwen2.5 VL model is supported by the PyTorch backend and can be found in the [Multimodal Feature Support Matrix (PyTorch Backend)](https://nvidia.github.io/TensorRT-LLM/models/supported-models.html).

Closing this issue based on discussions above. Please feel free to open a new one if the problem persists in the latest release. Thank you!