Hugging Face's logo

Spaces:
arcee-ai
/
Benchmarks
Running

App Files Community
Benchmarks
File size: 2,473 Bytes 
0c0f086
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
"""Module containing performance results for the Arcee-Scribe model."""

results_arcee_scribe = {
    "name": "Arcee-Scribe",
    "modelType": "InternLM2.5 8B",
    "configurations": [
        {
            "instanceType": "g5.2xlarge",
            "quantization": "none",
            "container": "DJL 0.28 vLLM",
            "status": "OK",
            "tokensPerSecond": 29,
            "notes": '"OPTION_MAX_MODEL_LEN": "32768",\n"TENSOR_PARALLEL_DEGREE": "max",',
        },
        {
            "instanceType": "g5.12xlarge",
            "quantization": "none",
            "container": "DJL 0.28 vLLM",
            "status": "OK",
            "tokensPerSecond": 65,
            "notes": '"OPTION_MAX_MODEL_LEN": "32768",\n"TENSOR_PARALLEL_DEGREE": "max",\nNot supported by AutoAWQ and AutoGPTQ',
        },
        {
            "instanceType": "g5.48xlarge",
            "quantization": "none",
            "container": "DJL 0.28 vLLM",
            "status": "OK",
            "tokensPerSecond": 80,
            "notes": '"OPTION_MAX_MODEL_LEN": "32768",\n"TENSOR_PARALLEL_DEGREE": "max",',
        },
        {
            "instanceType": "g6.2xlarge",
            "quantization": "none",
            "container": "DJL 0.28 vLLM",
            "status": "OK",
            "tokensPerSecond": 16,
            "notes": '"OPTION_MAX_MODEL_LEN": "4096"',
        },
        {
            "instanceType": "g6.12xlarge",
            "quantization": "none",
            "container": "DJL 0.28 vLLM",
            "status": "OK",
            "tokensPerSecond": 50,
            "notes": '"OPTION_MAX_MODEL_LEN": "32768",\n"TENSOR_PARALLEL_DEGREE": "max",',
        },
        {
            "instanceType": "g6.48xlarge",
            "quantization": "none",
            "container": "DJL 0.28 vLLM",
            "status": "OK",
            "tokensPerSecond": 69,
            "notes": '"OPTION_MAX_MODEL_LEN": "32768",\n"TENSOR_PARALLEL_DEGREE": "max",',
        },
        {
            "instanceType": "g6e.2xlarge",
            "quantization": "none",
            "container": "SGLang 0.2.13",
            "status": "OK",
            "tokensPerSecond": 46,
        },
        {
            "instanceType": "p4d.24xlarge",
            "quantization": "none",
            "container": "DJL 0.28 vLLM",
            "status": "OK",
            "tokensPerSecond": 82,
            "notes": '"OPTION_MAX_MODEL_LEN": "32768",\n"TENSOR_PARALLEL_DEGREE": "max",',
        },
    ],
}