Content
@
0 reply
0 recast
0 reaction
Frank (d/acc) 🎩 💜
@gptgod
When AMD GPU available from runpod, I will test the vllm inference performance. Looking forward it https://rocm.blogs.amd.com/artificial-intelligence/llm-inference-optimize/README.html
0 reply
0 recast
0 reaction
