Update on the development branch

[kaiyux]

Hi,

The TensorRT-LLM team is pleased to announce that we have pushed an update to the development branch (and the Triton backend) this Nov 19, 2024.

This update includes:

• Model Support
  • Added support for EAGLE. Refer to examples/eagle/README.md.
  • Added support for Qwen2-VL. Refer to the “Qwen2-VL” section of examples/multimodal/README.md.
  • Added multimodal evaluation examples. Refer to examples/multimodal.
• API
  • Added the enable_chunked_prefill flag to the LlmArgs of the LLM API.
  • Integrated BERT and RoBERTa models to the trtllm-build command.

Thanks,
The TensorRT-LLM Engineering Team