Update inference-cache-config/llama3-70b.json
Browse files
inference-cache-config/llama3-70b.json
CHANGED
@@ -4,13 +4,13 @@
|
|
4 |
"batch_size": 1,
|
5 |
"sequence_length": 4096,
|
6 |
"num_cores": 24,
|
7 |
-
"auto_cast_type": "
|
8 |
},
|
9 |
{
|
10 |
"batch_size": 4,
|
11 |
"sequence_length": 4096,
|
12 |
"num_cores": 24,
|
13 |
-
"auto_cast_type": "
|
14 |
}
|
15 |
]
|
16 |
}
|
|
|
4 |
"batch_size": 1,
|
5 |
"sequence_length": 4096,
|
6 |
"num_cores": 24,
|
7 |
+
"auto_cast_type": "bf16"
|
8 |
},
|
9 |
{
|
10 |
"batch_size": 4,
|
11 |
"sequence_length": 4096,
|
12 |
"num_cores": 24,
|
13 |
+
"auto_cast_type": "bf16"
|
14 |
}
|
15 |
]
|
16 |
}
|