mutkach

Async HTTP Python Client not working properly

1

**Description** `UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa6 in position 5: invalid start byte` when requesting a model config using an async http client. When observing the http response directly...

Mllama ignores input image when deployed in triton

2

### System Info cpu: x86_64 mem: 128G gpu: H100 80G docker: tritonserver:24.12-trtllm-python-py3 Cuda: 12.6 Driver: 535.216.01 TensorRT: 10.7.0 TensorRT-LLM: v0.16.0 ### Who can help? @kaiyux @byshiue ### Information - [x]...