Categories
Misc

Just Released: NVIDIA TensorRT-LLM 0.13.0

Decorative image of an atomic model icon connected to a computer monitor.Updates include tensor parallel support for Mamba2, sparse mixer normalization for MoE models, and more.Decorative image of an atomic model icon connected to a computer monitor.

Updates include tensor parallel support for Mamba2, sparse mixer normalization for MoE models, and more.

Source

Leave a Reply

Your email address will not be published. Required fields are marked *