Add phi4 cached configurations
Browse files
inference-cache-config/phi4.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"microsoft/Phi-3-mini-4k-instruct": [
|
3 |
+
{
|
4 |
+
"batch_size": 1,
|
5 |
+
"sequence_length": 4096,
|
6 |
+
"num_cores": 2,
|
7 |
+
"auto_cast_type": "bf16"
|
8 |
+
},
|
9 |
+
{
|
10 |
+
"batch_size": 4,
|
11 |
+
"sequence_length": 4096,
|
12 |
+
"num_cores": 2,
|
13 |
+
"auto_cast_type": "bf16"
|
14 |
+
}
|
15 |
+
],
|
16 |
+
"microsoft/phi-4": [
|
17 |
+
{
|
18 |
+
"batch_size": 1,
|
19 |
+
"sequence_length": 4096,
|
20 |
+
"num_cores": 10,
|
21 |
+
"auto_cast_type": "bf16"
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"batch_size": 16,
|
25 |
+
"sequence_length": 4096,
|
26 |
+
"num_cores": 10,
|
27 |
+
"auto_cast_type": "bf16"
|
28 |
+
}
|
29 |
+
]
|
30 |
+
}
|