l3jin·3 lata temu·discussUniversal deployment is indeed attractive. I have tested the Llama2-70B on 7900 XTX. Love the performance!Also saw a report earlier today on MLC’s discord about AMD MI-100:GPU Count | Model Size | Prefill Speed | Decode Speed1 | 33b | 102.2 | 22.32 | 33b | 112.3 | 33.04 | 33b | 144.8 | 41.2
l3jin·3 lata temu·discussCooool! We can use Stable Diffusion models on chrome.It can generate any image I want within 2mins:)
Also saw a report earlier today on MLC’s discord about AMD MI-100:
GPU Count | Model Size | Prefill Speed | Decode Speed
1 | 33b | 102.2 | 22.3
2 | 33b | 112.3 | 33.0
4 | 33b | 144.8 | 41.2