llama-cpp: set batch size to 4096
All checks were successful
Build and Deploy / deploy (push) Successful in 1m22s
All checks were successful
Build and Deploy / deploy (push) Successful in 1m22s
This commit is contained in:
@@ -40,6 +40,10 @@ in
|
||||
"--metrics"
|
||||
"--alias"
|
||||
modelAlias
|
||||
"-b"
|
||||
"4096"
|
||||
"-ub"
|
||||
"4096"
|
||||
];
|
||||
};
|
||||
|
||||
|
||||
Reference in New Issue
Block a user