bot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 5 months agoAMD's MI300X Outperforms Nvidia's H100 for LLM Inferencewww.blog.tensorwave.comexternal-linkmessage-square2fedilinkarrow-up19arrow-down10file-text
arrow-up19arrow-down1external-linkAMD's MI300X Outperforms Nvidia's H100 for LLM Inferencewww.blog.tensorwave.combot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 5 months agomessage-square2fedilinkfile-text
minus-squarefubarxlinkfedilinkarrow-up5·5 months agoWhy are they only testing inference vs training? Not many companies are going to want to deploy their own public-facing chatbot service. But almost everyone in this space is going to want to train their models, which is where the performance boost comes in.
Why are they only testing inference vs training?
Not many companies are going to want to deploy their own public-facing chatbot service. But almost everyone in this space is going to want to train their models, which is where the performance boost comes in.