Init

dmatora · May 2, 2024 · 055772a · 055772a
commit 055772a
Show file tree

Hide file tree

Showing 3 changed files with 92 additions and 0 deletions.
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1 @@
+.idea
diff --git a/README.md b/README.md
@@ -0,0 +1,21 @@
+# LLM Inference Speeds
+
+This repository contains benchmark data for various Large Language Models (LLM) based on their inference speeds measured in tokens per second. The benchmarks are performed across different hardware configurations using the prompt "tell a story".
+
+## About the Data
+
+The data represents the performance of several LLMs, detailing the tokens processed per second on specific hardware setups. Each entry includes the model name, the hardware used, and the measured speed.
+
+## Explore the Benchmarks
+
+You can view and interact with the benchmark data through a searchable table on our GitHub Pages site. Use the search field to filter by model name and explore different hardware performances.
+
+**[View the Inference Speeds Table](https://dmatora.github.io/inference-speed/)**
+
+## Contributing
+
+Contributions to the benchmark data are welcome! Please refer to the contributing guidelines for more information on how you can contribute.
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
diff --git a/index.html b/index.html
@@ -0,0 +1,70 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>LLM Inference Speeds</title>
+    <style>
+        body { font-family: Arial, sans-serif; }
+        input { margin: 20px 0; padding: 10px; width: 200px; }
+        table { width: 100%; border-collapse: collapse; }
+        th, td { padding: 10px; border: 1px solid #ddd; text-align: left; }
+        th { background-color: #f2f2f2; }
+    </style>
+</head>
+<body>
+<h1>LLM Inference Speeds</h1>
+<input type="text" id="searchInput" onkeyup="filterModels()" placeholder="Search for models...">
+
+<table id="dataTable">
+    <thead>
+    <tr>
+        <th>Model</th>
+        <th>Hardware</th>
+        <th>Speed</th>
+    </tr>
+    </thead>
+    <tbody>
+    </tbody>
+</table>
+
+<script>
+    document.addEventListener('DOMContentLoaded', function() {
+        fetch('data.json')
+            .then(response => response.json())
+            .then(data => {
+                const tableBody = document.getElementById('dataTable').getElementsByTagName('tbody')[0];
+                data.forEach(item => {
+                    let row = tableBody.insertRow();
+                    let cell1 = row.insertCell(0);
+                    let cell2 = row.insertCell(1);
+                    let cell3 = row.insertCell(2);
+                    cell1.textContent = item.model;
+                    cell2.textContent = item.hardware;
+                    cell3.textContent = item.speed;
+                });
+            })
+            .catch(error => console.error('Error loading the data:', error));
+    });
+
+    function filterModels() {
+        var input, filter, table, tr, td, i, txtValue;
+        input = document.getElementById("searchInput");
+        filter = input.value.toUpperCase();
+        table = document.getElementById("dataTable");
+        tr = table.getElementsByTagName("tr");
+        for (i = 0; i < tr.length; i++) {
+            td = tr[i].getElementsByTagName("td")[0];
+            if (td) {
+                txtValue = td.textContent || td.innerText;
+                if (txtValue.toUpperCase().indexOf(filter) > -1) {
+                    tr[i].style.display = "";
+                } else {
+                    tr[i].style.display = "none";
+                }
+            }
+        }
+    }
+</script>
+</body>
+</html>