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
I see that most of the x86 acceleration APIs are supported in llama.cpp, which is great! Intel AMX seems to have even more potential for speeding up inference.
AMX is support by Intel's latest server and workstation CPUs. Right now, the performance on my Intel w7-2495 AMX-enabled system (eval ~8 tokens per second) is lower than my MacBook Pro M1 (eval ~11 tokens per second).
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
-
I see that most of the x86 acceleration APIs are supported in llama.cpp, which is great! Intel AMX seems to have even more potential for speeding up inference.
AMX is support by Intel's latest server and workstation CPUs. Right now, the performance on my Intel w7-2495 AMX-enabled system (eval ~8 tokens per second) is lower than my MacBook Pro M1 (eval ~11 tokens per second).
Beta Was this translation helpful? Give feedback.
All reactions