Benchmarking Llama 3.1 405B on 8x AMD MI300X GPUs - dstack - discu.eu

Hacker News

Benchmarking Llama 3.1 405B on 8x AMD MI300X GPUs https://dstack.ai/blog/amd-mi300x-inference-benchmark/ 3 comments 9/10/2024

Linked pages

Rent Cloud GPUs from $0.2/hour https://runpod.io 4 comments

Related searches:

Search whole site: site:dstack.ai

Search title: Benchmarking Llama 3.1 405B on 8x AMD MI300X GPUs - dstack

See how to search.

Submit link to: