{
 "<h1>Cache for Intermediate Activations</h1>\n<p>During inference the model outputs token by token. We use this simple cache to store key&#x27;s and value&#x27;s attention layers, so that we don&#x27;t have to recompute them for previous tokens.</p>\n": "<h1>\u4e2d\u9593\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3\u7528\u30ad\u30e3\u30c3\u30b7\u30e5</h1>\n<p>\u63a8\u8ad6\u4e2d\u3001\u30e2\u30c7\u30eb\u306f\u30c8\u30fc\u30af\u30f3\u3054\u3068\u306b\u51fa\u529b\u3057\u307e\u3059\u3002\u3053\u306e\u30b7\u30f3\u30d7\u30eb\u306a\u30ad\u30e3\u30c3\u30b7\u30e5\u3092\u4f7f\u3063\u3066\u30ad\u30fc\u3068\u5024\u306e\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30ec\u30a4\u30e4\u30fc\u3092\u683c\u7d0d\u3059\u308b\u306e\u3067\u3001\u4ee5\u524d\u306e\u30c8\u30fc\u30af\u30f3\u3067\u305d\u308c\u3089\u3092\u518d\u8a08\u7b97\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u305b\u3093</p>\u3002\n",
 "<h2>Cache</h2>\n<p>This maintains a key-value cache and queues push values and pop them in the same order. The queues are useful since we have multiple attention layers.</p>\n": "<h2>\u30ad\u30e3\u30c3\u30b7\u30e5</h2>\n<p>\u3053\u308c\u306b\u3088\u308a\u3001\u30ad\u30fc\u3068\u5024\u306e\u30ad\u30e3\u30c3\u30b7\u30e5\u304c\u7dad\u6301\u3055\u308c\u3001\u5024\u306e\u30d7\u30c3\u30b7\u30e5\u3068\u30dd\u30c3\u30d7\u304c\u540c\u3058\u9806\u5e8f\u3067\u30ad\u30e5\u30fc\u306b\u5165\u308c\u3089\u308c\u307e\u3059\u3002\u30ad\u30e5\u30fc\u306f\u8907\u6570\u306e\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30ec\u30a4\u30e4\u30fc\u304c\u3042\u308b\u306e\u3067\u4fbf\u5229\u3067\u3059</p>\u3002\n",
 "<h3>Cache a value</h3>\n<ul><li><span translate=no>_^_0_^_</span>  is the name of the value to be cached </li>\n<li><span translate=no>_^_1_^_</span>  is the value</li></ul>\n": "<h3>\u5024\u3092\u30ad\u30e3\u30c3\u30b7\u30e5\u3059\u308b</h3>\n<ul><li><span translate=no>_^_0_^_</span>\u30ad\u30e3\u30c3\u30b7\u30e5\u3055\u308c\u308b\u5024\u306e\u540d\u524d</li>\n<li><span translate=no>_^_1_^_</span>\u306f\u5024\u3067\u3059</li></ul>\n",
 "<h3>Clear a cache value</h3>\n<ul><li><span translate=no>_^_0_^_</span>  is the name used when caching</li></ul>\n": "<h3>\u30ad\u30e3\u30c3\u30b7\u30e5\u5024\u3092\u30af\u30ea\u30a2\u3059\u308b</h3>\n<ul><li><span translate=no>_^_0_^_</span>\u30ad\u30e3\u30c3\u30b7\u30e5\u6642\u306b\u4f7f\u7528\u3055\u308c\u308b\u540d\u524d\u3067\u3059</li></ul>\n",
 "<h3>Clear cache</h3>\n": "<h3>\u30ad\u30e3\u30c3\u30b7\u30e5\u3092\u30af\u30ea\u30a2</h3>\n",
 "<h3>Get the cache instance</h3>\n<ul><p><em>Returns</em>  the cache instance</p></ul>\n": "<h3>\u30ad\u30e3\u30c3\u30b7\u30e5\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u3092\u53d6\u5f97</h3>\n<ul><p><em>\u30ad\u30e3\u30c3\u30b7\u30e5\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u3092\u8fd4\u3057\u307e\u3059</em></p></ul>\n",
 "<h3>Pop from a queue</h3>\n<ul><li><span translate=no>_^_0_^_</span>  is the name of the queue </li>\n<p><em>Returns</em>  the value</p></ul>\n": "<h3>\u30ad\u30e5\u30fc\u304b\u3089\u30dd\u30c3\u30d7\u3059\u308b</h3>\n<ul><li><span translate=no>_^_0_^_</span>\u306f\u30ad\u30e5\u30fc\u306e\u540d\u524d\u3067\u3059</li>\n<p><em>\u5024\u3092\u8fd4\u3059</em></p></ul>\n",
 "<h3>Push a value to a queue</h3>\n<ul><li><span translate=no>_^_0_^_</span>  is the name of the queue </li>\n<li><span translate=no>_^_1_^_</span>  is the value to be pushed</li></ul>\n": "<h3>\u5024\u3092\u30ad\u30e5\u30fc\u306b\u30d7\u30c3\u30b7\u30e5</h3>\n<ul><li><span translate=no>_^_0_^_</span>\u306f\u30ad\u30e5\u30fc\u306e\u540d\u524d\u3067\u3059</li>\n<li><span translate=no>_^_1_^_</span>\u30d7\u30c3\u30b7\u30e5\u3059\u308b\u5024\u3067\u3059</li></ul>\n",
 "<h3>Retrieve a value from cache</h3>\n<ul><li><span translate=no>_^_0_^_</span>  is the name used when caching </li>\n<li><span translate=no>_^_1_^_</span>  is the default value if the cache is empty </li>\n<p><em>Returns</em>  the cached value</p></ul>\n": "<h3>\u30ad\u30e3\u30c3\u30b7\u30e5\u304b\u3089\u5024\u3092\u53d6\u5f97</h3>\n<ul><li><span translate=no>_^_0_^_</span>\u30ad\u30e3\u30c3\u30b7\u30e5\u6642\u306b\u4f7f\u7528\u3055\u308c\u308b\u540d\u524d\u3067\u3059</li>\n<li><span translate=no>_^_1_^_</span>\u30ad\u30e3\u30c3\u30b7\u30e5\u304c\u7a7a\u306e\u5834\u5408\u306e\u30c7\u30d5\u30a9\u30eb\u30c8\u5024\u3067\u3059</li>\n<p><em>\u30ad\u30e3\u30c3\u30b7\u30e5\u3055\u308c\u305f\u5024\u3092\u8fd4\u3057\u307e\u3059</em></p></ul>\n",
 "<h3>Return the size of the queue</h3>\n<ul><li><span translate=no>_^_0_^_</span>  is the name of the queue </li>\n<p><em>Returns</em>  size of the queue if exists else None</p></ul>\n": "<h3>\u30ad\u30e5\u30fc\u306e\u30b5\u30a4\u30ba\u3092\u8fd4\u3059</h3>\n<ul><li><span translate=no>_^_0_^_</span>\u306f\u30ad\u30e5\u30fc\u306e\u540d\u524d\u3067\u3059</li>\n<p><em>\u30ad\u30e5\u30fc\u304c\u5b58\u5728\u3059\u308b\u5834\u5408\u306f\u30ad\u30e5\u30fc\u306e\u30b5\u30a4\u30ba\u3092\u8fd4\u3057\u307e\u3059</em>\u3002\u305d\u308c\u4ee5\u5916\u306e\u5834\u5408\u306f None</p></ul>\n",
 "<p>Create an empty queue if it&#x27;s not present </p>\n": "<p>\u5b58\u5728\u3057\u306a\u3044\u5834\u5408\u306f\u7a7a\u306e\u30ad\u30e5\u30fc\u3092\u4f5c\u6210</p>\n",
 "<p>Push to the queue </p>\n": "<p>\u30ad\u30e5\u30fc\u306b\u30d7\u30c3\u30b7\u30e5</p>\n",
 "<p>Singleton for cache </p>\n": "<p>\u30ad\u30e3\u30c3\u30b7\u30e5\u7528\u30b7\u30f3\u30b0\u30eb\u30c8\u30f3</p>\n",
 "Cache for Intermediate Activations": "\u4e2d\u9593\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3\u7528\u30ad\u30e3\u30c3\u30b7\u30e5",
 "Cache for intermediate activations for faster inference.": "\u63a8\u8ad6\u3092\u9ad8\u901f\u5316\u3059\u308b\u305f\u3081\u306e\u4e2d\u9593\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3\u7528\u306e\u30ad\u30e3\u30c3\u30b7\u30e5\u3002"
}