Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
645
optimum-neuron-cache
File size: 2,582 Bytes 
25e9ebd
 
 
 
 
 
 
 
f8538f0
 
 
 
 
 
25e9ebd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f8538f0
 
 
 
 
 
25e9ebd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f8538f0
 
 
 
 
 
25e9ebd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f8538f0
 
 
 
 
 
25e9ebd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
 
{
  "meta-llama/Llama-3.1-8B": [
    {
      "batch_size": 1,
      "sequence_length": 4096,
      "tensor_parallel_size": 4,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 1,
      "sequence_length": 16384,
      "tensor_parallel_size": 4,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 8,
      "sequence_length": 4096,
      "tensor_parallel_size" : 4,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 32,
      "sequence_length": 4096,
      "tensor_parallel_size": 4,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 64,
      "sequence_length": 4096,
      "tensor_parallel_size": 4,
      "instance_type" : "trn2"
    }
  ],
  "meta-llama/Llama-3.2-1B": [
    {
      "batch_size": 1,
      "sequence_length": 4096,
      "tensor_parallel_size" : 4,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 1,
      "sequence_length": 16384,
      "tensor_parallel_size" : 4,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 4,
      "sequence_length": 4096,
      "tensor_parallel_size" : 4,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 64,
      "sequence_length": 4096,
      "tensor_parallel_size" : 4,
      "instance_type" : "trn2"
    }
  ],
  "meta-llama/Llama-3.2-3B": [
    {
      "batch_size": 1,
      "sequence_length": 4096,
      "tensor_parallel_size" : 4,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 1,
      "sequence_length": 16384,
      "tensor_parallel_size" : 4,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 64,
      "sequence_length": 4096,
      "tensor_parallel_size" : 4,
      "instance_type" : "trn2"
    }
  ],
  "TinyLlama/TinyLlama-1.1B-Chat-v1.0": [
    {
      "batch_size": 1,
      "sequence_length": 2048,
      "tensor_parallel_size" : 4,
      "instance_type" : "trn2"
    }
  ],
  "meta-llama/Llama-3.3-70B-Instruct": [
    {
      "batch_size": 32,
      "sequence_length": 4096,
      "tensor_parallel_size": 32,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 1,
      "sequence_length": 4096,
      "tensor_parallel_size": 64,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 1,
      "sequence_length": 16384,
      "tensor_parallel_size": 64,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 32,
      "sequence_length": 4096,
      "tensor_parallel_size": 64,
      "instance_type" : "trn2"
    },
    {
      "batch_size": 64,
      "sequence_length": 4096,
      "tensor_parallel_size": 64,
      "instance_type" : "trn2"
    }
  ]
}