Hugging Face's logo

Spaces:
Xenova
/
webgpu-embedding-benchmark
Running

App Files Community
105
webgpu-embedding-benchmark
File size: 2,537 Bytes 
fde729d
 
 
 
 
 
 
377005e
 
fde729d
 
 
 
 
 
 
377005e
fde729d
 
 
 
 
 
 
 
 
 
 
 
377005e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fde729d
 
 
 
 
 
 
 
377005e
fde729d
377005e
 
fde729d
 
 
377005e
20be0fa
 
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
 
<!DOCTYPE html>
<html lang="en">

<head>
  <meta charset="UTF-8" />
  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
  <title>Transformers.js | WebGPU Benchmark</title>
  <script type="module" crossorigin src="/assets/index-D9dUKbnn.js"></script>
  <link rel="stylesheet" crossorigin href="/assets/index-BZcCtzqA.css">
</head>

<body>
  <h1>
    <a href="http://github.com/xenova/transformers.js" target="_blank">🤗 Transformers.js</a> WebGPU Benchmark
  </h1>
  <p>
    This benchmark measures the execution time of BERT-based embedding models
    using the WASM and WebGPU execution providers across different batch sizes.
  </p>
  <div id="chart-container">
    <canvas id="chart"></canvas>
  </div>
  <div>
    <button id="start" disabled>Start Benchmark</button>
    <button id="stop" disabled>Stop Benchmark</button>
  </div>
  <label id="status"></label>
  <details open>
    <summary>Options</summary>
    <div>
      <input class="tests" type="checkbox" value="WASM (int8)" data-color="33,150,243" data-device="wasm"

        data-dtype="int8"> WASM (int8)<br />
      <input class="tests" type="checkbox" value="WASM (fp16)" data-color="63,81,181" data-device="wasm"

        data-dtype="fp16"> WASM (fp16)<br />
      <input class="tests" type="checkbox" value="WASM (fp32)" data-color="46,204,113" data-device="wasm"

        data-dtype="fp32" checked> WASM (fp32)<br />
      <!-- <input class="tests" type="checkbox" value="WebGPU (int8)" data-color="233,30,99" data-device="webgpu"

        data-dtype="int8"> WebGPU (int8)<br /> -->
      <input class="tests" type="checkbox" value="WebGPU (fp16)" data-color="255,193,7" data-device="webgpu"

        data-dtype="fp16"> WebGPU (fp16)<br />
      <input class="tests" type="checkbox" value="WebGPU (fp32)" data-color="0,150,136" data-device="webgpu"

        data-dtype="fp32" checked> WebGPU (fp32)<br />
    </div>
    <hr />
    <div>
      <label>Model ID</label>
      <input id="model-id" value="Xenova/all-MiniLM-L6-v2" />
    </div>
    <div>
      <label>Batch sizes</label>
      <input id="batch-sizes" value="1, 2, 4, 8, 16, 32" />
    </div>
    <div>
      <label>Sequence length</label>
      <input id="sequence-length" type="number" min="1" max="512" value="512" />
    </div>
    <hr />
    <div>
      <input id="x-scale" type="checkbox" /> Log scale (x) <br />
      <input id="y-scale" type="checkbox" /> Log scale (y) <br />
    </div>
  </details>

</body>

</html>