Notices by condret :verified: :ancom: (condret@fedi.absturztau.be), page 4
-
Embed this notice
condret :verified: :ancom: (condret@fedi.absturztau.be)'s status on Tuesday, 24-Oct-2023 16:39:54 JST condret :verified: :ancom: @kaia why cuda? -
Embed this notice
condret :verified: :ancom: (condret@fedi.absturztau.be)'s status on Tuesday, 24-Oct-2023 16:39:52 JST condret :verified: :ancom: @kaia i mean https://github.com/ROCm-Developer-Tools/HIPIFY exists, so you don't have to necessarily rely on cuda apis -
Embed this notice
condret :verified: :ancom: (condret@fedi.absturztau.be)'s status on Tuesday, 24-Oct-2023 16:24:25 JST condret :verified: :ancom: @kaia as long as you don't want to heavily train models, it could work with some older gpu just fine, i believe.
a friend runs some llama models on cpu.In conversation from fedi.absturztau.be permalink -
Embed this notice
condret :verified: :ancom: (condret@fedi.absturztau.be)'s status on Tuesday, 24-Oct-2023 16:19:50 JST condret :verified: :ancom: @kaia gpus for what purpose? In conversation from fedi.absturztau.be permalink