You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
What threads are responsible for calling ggml_backend_tensor_alloc? I can see from using --numa distribute that tok/sec increases, so something is happening, but it's hard to tell how many threads there are and what is actually calling ggml_backend_tensor_alloc , since my understanding is cudaMallocHost itself isn't NUMA aware, the thread calling it must be.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
What threads are responsible for calling
ggml_backend_tensor_alloc
? I can see from using--numa distribute
that tok/sec increases, so something is happening, but it's hard to tell how many threads there are and what is actually callingggml_backend_tensor_alloc
, since my understanding iscudaMallocHost
itself isn't NUMA aware, the thread calling it must be.Beta Was this translation helpful? Give feedback.
All reactions