AMD wants people to remember that Nvidia\u2019s not the only company selling AI chips<\/a>. It\u2019s announced the availability of new accelerators and processors geared toward running large language models, or LLMs.\u00a0<\/p>\n<\/div>\n The chipmaker unveiled the Instinct MI300X accelerator and the Instinct M1300A accelerated processing unit (APU), which the company said works to train and run LLMs. The company said the MI300X has 1.5 times more memory capacity than the previous M1250X version. Both new products have better memory capacity and are more energy-efficient than their predecessors, said AMD.\u00a0<\/p>\n<\/div>\n \u201cLLMs continue to increase in size and complexity, requiring massive amounts of memory and compute,\u201d AMD CEO Lisa Su said. \u201cAnd we know the availability of GPUs is the single most important driver of AI adoption.\u201d<\/p>\n<\/div>\n Su said during a presentation that MI300X \u201cis the highest performing accelerator in the world.\u201d She claimed MI300X is comparable to Nvidia\u2019s H100 chips in training LLMs but performs better on the inference side \u2014 1.4 times better than H100 when working with Meta\u2019s Llama 2, a 70 billion parameter LLM.\u00a0<\/p>\n<\/div>\n AMD partnered with Microsoft to put MI300X in its Azure virtual machines. Microsoft CTO Kevin Scott, a guest during Su\u2019s speech, also announced the Azure ND MI300X virtual machines<\/a> \u2014 first revealed in November \u2014 are now available on preview. Meta also announced it will deploy MI300 processors in its data centers.\u00a0<\/p>\n<\/div>\n Su said AMD released the MI300A APU for data centers, which she said are expected to grow its total addressable market to $45 billion. APUs generally combine CPUs and GPUs for faster processing. AMD said the MI300A offers higher-performance computing, faster model training, and a 30 times energy efficiency improvement. Compared to the H100, AMD said it has 1.6 times the memory capacity. It also features unified memory, so there is no need to move data from different devices anymore.\u00a0<\/p>\n<\/div>\n MI300A will power the El Capitan supercomputer built by Hewlett Packard Enterprise at the Lawrence Livermore National Laboratory. El Capitan is considered one of the most powerful supercomputers and is expected to deliver more than two exaflops of performance.\u00a0<\/p>\n<\/div>\n