NVIDIA's opt-in MXFP8 kernel hits 2.5x in a Kimi K3 microbenchmark on one VR200

The TensorRT-LLM change is off by default and targets replicated shared experts on SM107.

By · Published

Black server racks line an aisle, with green indicator lights and a prominent NVIDIA logo on a front panel.

The TensorRT-LLM change is off by default and targets replicated shared experts on SM107.