ValeGian issues

Repositories
Issues
Comments

Results 2 issues of


                                            ValeGian

Build failure when using FP8 quantized Medusa heads

### System Info CPU architecture: x86_64 GPU: NVIDIA H100 Libraries TensorRT-LLM: v0.11.0 TensorRT: 10.1.0 Modelopt: 0.13.1 CUDA: 12.3 NVIDIA driver version: 535.129.03 ### Issue Hello, I'm experiencing a failure when...

Added mistral model support

## Motivation This PR aims to add support to train mistral models ## Modifications - Added distributed model impl for mistral model architecture - Added template to registry - Added...