Re:AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
by muxr on Sunday June 16, 2024 @06:41PM
(#40700705)
I don't understand why they should use TensorRT. vLLM is much more popular and it was actually written for Nvidia. It also supports AMD hardware, so it's the appropriate tool to compare.
[ Parent
| on HN ]
There are no comments on this comment yet.