Buckets:

hf-doc-build
/

doc

Files
xet
hf-doc-build/doc / diffusers /main /ja /quantization /overview.html
mishig
1 day ago
download
raw
36.3 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;はじめる&quot;,&quot;local&quot;:&quot;getting-started&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;パイプラインレベルの量子化&quot;,&quot;local&quot;:&quot;pipeline-level-quantization&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;基本的な量子化&quot;,&quot;local&quot;:&quot;basic-quantization&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;高度な量子化&quot;,&quot;local&quot;:&quot;advanced-quantization&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;事前量子化済みチェックポイントの読み込み&quot;,&quot;local&quot;:&quot;loading-prequantized-checkpoints&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;リソース&quot;,&quot;local&quot;:&quot;resources&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
		<link href="/docs/diffusers/main/en/_app/immutable/entry/start.D3LnKZ4R.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/BF9UNEM9.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DPnyVmXs.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/entry/app.C0rBoMxR.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DSGUT_OW.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/C045MWWx.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DnVIJfC5.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/nodes/0.DTZsP_3B.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/IaDvMxLQ.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/nodes/313.C7ff02l6.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/bKdwVYpU.js" rel="modulepreload">
		<!--cubdu--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Getting started&quot;,&quot;local&quot;:&quot;getting-started&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Pipeline-level quantization&quot;,&quot;local&quot;:&quot;pipeline-level-quantization&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Basic quantization&quot;,&quot;local&quot;:&quot;basic-quantization&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Advanced quantization&quot;,&quot;local&quot;:&quot;advanced-quantization&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Loading prequantized checkpoints&quot;,&quot;local&quot;:&quot;loading-prequantized-checkpoints&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Resources&quot;,&quot;local&quot;:&quot;resources&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
		<link href="/docs/diffusers/main/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;"><div dir="ltr" class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----></span> <span dir="auto">Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg><!----></button></div> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="getting-started" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#getting-started"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->はじめる<!----></span></h1><!--]--><!----> <p>Quantizationは、元のデータの精度を維持しつつ、より少ないビット数でデータを表現することに焦点を当てています。これは通常、同じ情報をより少ないビット数で表現するためにデータ型を変換することを意味します。例えば、モデルの重みが32ビット浮動小数点数として保存されている場合、これを16ビット浮動小数点数にQuantizationすると、モデルサイズが半分になり、保存が容易になり、メモリ使用量が削減されます。精度が低くなることで、より少ないビット数での計算に要する時間が短くなるため、推論の高速化にもつながります。</p> <p>Diffusers は、<a href="../api/pipelines/flux">Flux</a> などの大規模な拡散モデルをより利用しやすくするために、複数の量子化バックエンドをサポートしています。このガイドでは、事前学習済みまたは非量子化のチェックポイントからパイプラインを初期化する際に、<a href="/docs/diffusers/main/ja/api/quantization#diffusers.PipelineQuantizationConfig">PipelineQuantizationConfig</a> クラスを使用してパイプラインを量子化する方法を示します。</p> <!--[1--><h2 class="relative group"><a id="pipeline-level-quantization" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#pipeline-level-quantization"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->パイプラインレベルの量子化<!----></span></h2><!--]--><!----> <p>量子化設定にどの程度のカスタマイズを適用したいかによって、<a href="/docs/diffusers/main/ja/api/quantization#diffusers.PipelineQuantizationConfig">PipelineQuantizationConfig</a>の使用方法は2つあります。</p> <ul><li>基本的なユースケースでは、<code>quant_backend</code>、<code>quant_kwargs</code>、<code>components_to_quantize</code> の引数を定義します。</li> <li>詳細な量子化制御を行うには、<code>quant_mapping</code>を定義して、個々のモデルコンポーネントに対する量子化設定を指定します。</li></ul> <!--[2--><h3 class="relative group"><a id="basic-quantization" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#basic-quantization"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->基本的な量子化<!----></span></h3><!--]--><!----> <p><a href="/docs/diffusers/main/ja/api/quantization#diffusers.PipelineQuantizationConfig">PipelineQuantizationConfig</a> を以下のパラメータで初期化します。</p> <ul><li><code>quant_backend</code> は使用する量子化バックエンドを指定します。現在サポートされているバックエンドには、<code>bitsandbytes_4bit</code>、<code>bitsandbytes_8bit</code>、<code>gguf</code>、<code>quanto</code>、<code>torchao</code> が含まれます。</li> <li><code>quant_kwargs</code> は、使用する量子化引数を指定します。</li></ul> <blockquote class="tip"><p>これらの <code>quant_kwargs</code> 引数は、バックエンドごとに異なります。各バックエンドの引数については、<a href="../api/quantization">Quantization API</a> のドキュメントを参照してください。</p></blockquote> <ul><li><p><code>components_to_quantize</code> は、パイプラインのどのコンポーネントを量子化するかを指定します。通常、transformer などの計算負荷が最も大きいコンポーネントを量子化すべきです。<a href="/docs/diffusers/main/ja/api/pipelines/flux#diffusers.FluxPipeline">FluxPipeline</a> のように複数のテキストエンコーダーを持つパイプラインでは、テキストエンコーダーも量子化の対象として検討すべきです。以下の例では、<a href="/docs/diffusers/main/ja/api/pipelines/flux#diffusers.FluxPipeline">FluxPipeline</a> の T5 テキストエンコーダーを量子化し、CLIP モデルはそのままにしています。</p> <p><code>components_to_quantize</code> は、複数のモデルを指定する場合はリストを、単一のモデルを指定する場合は文字列を受け取ります。</p></li></ul> <p>以下の例では、<a href="/docs/diffusers/main/ja/api/quantization#diffusers.BitsAndBytesConfig">BitsAndBytesConfig</a>から <code>load_in_4bit</code>、<code>bnb_4bit_quant_type</code>、<code>bnb_4bit_compute_dtype</code> という引数を指定して、bitsandbytes バックエンドを読み込みます。</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> コピーしました</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline
<span class="hljs-keyword">from</span> diffusers.quantizers <span class="hljs-keyword">import</span> PipelineQuantizationConfig

pipeline_quant_config = PipelineQuantizationConfig(
    quant_backend=<span class="hljs-string">&quot;bitsandbytes_4bit&quot;</span>,
    quant_kwargs={<span class="hljs-string">&quot;load_in_4bit&quot;</span>: <span class="hljs-literal">True</span>, <span class="hljs-string">&quot;bnb_4bit_quant_type&quot;</span>: <span class="hljs-string">&quot;nf4&quot;</span>, <span class="hljs-string">&quot;bnb_4bit_compute_dtype&quot;</span>: torch.bfloat16},
    components_to_quantize=[<span class="hljs-string">&quot;transformer&quot;</span>, <span class="hljs-string">&quot;text_encoder_2&quot;</span>],
)<!----></pre></div><!----> <p>パイプラインを量子化するには、<code>pipeline_quant_config</code> を <a href="/docs/diffusers/main/ja/api/pipelines/overview#diffusers.DiffusionPipeline.from_pretrained">from_pretrained()</a> に渡します。</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> コピーしました</div><!----></button><!----></div> <pre class="language-py "><!---->pipe = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;black-forest-labs/FLUX.1-dev&quot;</span>,
    quantization_config=pipeline_quant_config,
    dtype=torch.bfloat16,
).to(<span class="hljs-string">&quot;cuda&quot;</span>)  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>

image = pipe(<span class="hljs-string">&quot;photo of a cute dog&quot;</span>).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <!--[2--><h3 class="relative group"><a id="advanced-quantization" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#advanced-quantization"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->高度な量子化<!----></span></h3><!--]--><!----> <p><code>quant_mapping</code> 引数により、パイプライン内の各コンポーネントの量子化方法をより詳細に指定できます。異なる量子化バックエンドを組み合わせることも可能です。</p> <p><a href="/docs/diffusers/main/ja/api/quantization#diffusers.PipelineQuantizationConfig">PipelineQuantizationConfig</a> を初期化し、<code>quant_mapping</code> を渡します。<code>quant_mapping</code> を使用すると、transformer や text encoder など、パイプライン内の各コンポーネントに対する量子化オプションを指定できます。</p> <p>以下の例では、transformerとテキストエンコーダーにそれぞれ2つの量子化バックエンド、<a href="/docs/diffusers/main/ja/api/quantization#diffusers.QuantoConfig">QuantoConfig</a>と<a href="https://huggingface.co/docs/transformers/main/en/main_classes/quantization#transformers.BitsAndBytesConfig" rel="nofollow">transformers.BitsAndBytesConfig</a>を使用しています。</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> コピーしました</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> BitsAndBytesConfig <span class="hljs-keyword">as</span> DiffusersBitsAndBytesConfig
<span class="hljs-keyword">from</span> diffusers.quantizers.quantization_config <span class="hljs-keyword">import</span> QuantoConfig
<span class="hljs-keyword">from</span> diffusers.quantizers <span class="hljs-keyword">import</span> PipelineQuantizationConfig
<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> BitsAndBytesConfig <span class="hljs-keyword">as</span> TransformersBitsAndBytesConfig

pipeline_quant_config = PipelineQuantizationConfig(
    quant_mapping={
        <span class="hljs-string">&quot;transformer&quot;</span>: QuantoConfig(weights_dtype=<span class="hljs-string">&quot;int8&quot;</span>),
        <span class="hljs-string">&quot;text_encoder_2&quot;</span>: TransformersBitsAndBytesConfig(
            load_in_4bit=<span class="hljs-literal">True</span>, compute_dtype=torch.bfloat16
        ),
    }
)<!----></pre></div><!----> <p><a href="https://huggingface.co/docs/transformers/main_classes/quantization#transformers.BitsAndBytesConfig" rel="nofollow">Transformers</a>には別のbitsandbytesバックエンドがあります。Transformers由来のコンポーネントには、<a href="https://huggingface.co/docs/transformers/main/en/main_classes/quantization#transformers.BitsAndBytesConfig" rel="nofollow">transformers.BitsAndBytesConfig</a>をインポートして使用する必要があります。例えば、<a href="/docs/diffusers/main/ja/api/pipelines/flux#diffusers.FluxPipeline">FluxPipeline</a>内の<code>text_encoder_2</code>はTransformersの<a href="https://huggingface.co/docs/transformers/main/en/model_doc/t5#transformers.T5EncoderModel" rel="nofollow">T5EncoderModel</a>であるため、<a href="/docs/diffusers/main/ja/api/quantization#diffusers.BitsAndBytesConfig">diffusers.BitsAndBytesConfig</a>ではなく<a href="https://huggingface.co/docs/transformers/main/en/main_classes/quantization#transformers.BitsAndBytesConfig" rel="nofollow">transformers.BitsAndBytesConfig</a>を使用する必要があります。</p> <blockquote class="tip"><p>これらの個別のインポートを管理したくない場合、または各パイプラインコンポーネントの由来が不明な場合は、上記の<a href="#basic-quantization">基本的な量子化</a>メソッドを使用してください。</p></blockquote> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> コピーしました</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> BitsAndBytesConfig <span class="hljs-keyword">as</span> DiffusersBitsAndBytesConfig
<span class="hljs-keyword">from</span> diffusers.quantizers <span class="hljs-keyword">import</span> PipelineQuantizationConfig
<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> BitsAndBytesConfig <span class="hljs-keyword">as</span> TransformersBitsAndBytesConfig

pipeline_quant_config = PipelineQuantizationConfig(
    quant_mapping={
        <span class="hljs-string">&quot;transformer&quot;</span>: DiffusersBitsAndBytesConfig(load_in_4bit=<span class="hljs-literal">True</span>, bnb_4bit_compute_dtype=torch.bfloat16),
        <span class="hljs-string">&quot;text_encoder_2&quot;</span>: TransformersBitsAndBytesConfig(
            load_in_4bit=<span class="hljs-literal">True</span>, compute_dtype=torch.bfloat16
        ),
    }
)<!----></pre></div><!----> <p>パイプラインを量子化するには、<code>pipeline_quant_config</code> を <a href="/docs/diffusers/main/ja/api/pipelines/overview#diffusers.DiffusionPipeline.from_pretrained">from_pretrained()</a> に渡します。</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> コピーしました</div><!----></button><!----></div> <pre class="language-py "><!---->pipe = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;black-forest-labs/FLUX.1-dev&quot;</span>,
    quantization_config=pipeline_quant_config,
    dtype=torch.bfloat16,
).to(<span class="hljs-string">&quot;cuda&quot;</span>)  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>

image = pipe(<span class="hljs-string">&quot;photo of a cute dog&quot;</span>).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="loading-prequantized-checkpoints" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#loading-prequantized-checkpoints"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->事前量子化済みチェックポイントの読み込み<!----></span></h2><!--]--><!----> <p>一部の量子化バックエンドは、すでに量子化されて Hub にアップロードされたチェックポイントの読み込みをサポートしています。この場合、量子化設定はモデルの <code>config.json</code> に保存され、自動的に読み込まれます。そのため、<a href="/docs/diffusers/main/ja/api/quantization#diffusers.PipelineQuantizationConfig">PipelineQuantizationConfig</a> を作成したり、<code>quantization_config</code> 引数を渡したりする必要はありません。</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> コピーしました</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;rootonchair/ERNIE-Image-Turbo-nunchaku-lite-nvfp4&quot;</span>,
    dtype=torch.bfloat16,
).to(<span class="hljs-string">&quot;cuda&quot;</span>)  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span><!----></pre></div><!----> <p>以下のバックエンドは、プリクオンタイズ済みチェックポイントの読み込みをそのままサポートしています。</p> <table><thead><tr><th>バックエンド</th><th>注記</th></tr></thead><tbody><tr><td><a href="./bitsandbytes">bitsandbytes</a></td><td>Config は <code>config.json</code> に保存されます。追加の引数は不要です。オンザフライでの量子化と、事前量子化済みチェックポイントの読み込みの両方をサポートしています。</td></tr><tr><td><a href="./torchao">torchao</a></td><td>上記と同様です。</td></tr><tr><td><a href="./gguf">GGUF</a></td><td>Model クラスで <code>from_single_file</code> を使用します。パイプラインレベルでの読み込みはサポートされていません。</td></tr><tr><td><a href="./bfl">BFL</a></td><td>Black Forest Labs の <code>fp8r</code> および <code>nvfp4</code> の単一ファイル形式のチェックポイントを <code>from_single_file</code> で読み込みます。パイプラインレベルでの読み込みはサポートされていません。</td></tr><tr><td><a href="./autoround">AutoRound</a></td><td>読み込みのみがサポートされています。まず、AutoRound CLIまたはPython APIで量子化してください。</td></tr><tr><td><a href="./nunchaku">Nunchaku Lite</a></td><td>Config は <code>config.json</code> に保存されます。<code>kernels</code> パッケージが必要です。読み込みのみサポートされています。</td></tr><tr><td><a href="./modelopt">ModelOpt</a></td><td>事前量子化済みモデルの読み込みのみがサポートされています。</td></tr><tr><td><a href="./sdnq">SDNQ</a></td><td><code>sdnq</code>パッケージが必要です。オンザフライでの量子化と、事前量子化済みモデルの読み込みの両方をサポートします。</td></tr></tbody></table> <!--[1--><h2 class="relative group"><a id="resources" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#resources"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->リソース<!----></span></h2><!--]--><!----> <p>量子化について詳しく学ぶには、以下のリソースをご覧ください。</p> <ul><li><p>量子化が初めての方は、DeepLearning.AI との協力により提供されている、初心者向けの以下のコースを参照することをお勧めします。</p> <ul><li><a href="https://www.deeplearning.ai/short-courses/quantization-fundamentals-with-hugging-face/" rel="nofollow">Hugging Faceによる量子化の基礎</a></li> <li><a href="https://www.deeplearning.ai/short-courses/quantization-in-depth/" rel="nofollow">量子化の深掘り</a></li></ul></li> <li><p>新しい量子化手法の追加にご興味がある場合は、<a href="https://huggingface.co/docs/transformers/main/en/quantization/contribute" rel="nofollow">新しい量子化手法の貢献ガイド</a>を参照してください。</p></li> <li><p>Transformers の量子化 <a href="https://huggingface.co/docs/transformers/quantization/overview#when-to-use-what" rel="nofollow">概要</a> では、異なる量子化バックエンドの長所と短所について概説しています。</p></li> <li><p><a href="https://huggingface.co/blog/diffusers-quantization" rel="nofollow">Diffusersにおける量子化バックエンドの探索</a>のブログ記事では、各量子化バックエンドの簡単な紹介、バックエンドの選択方法、および量子化と他のメモリ最適化の組み合わせについて解説しています。</p></li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/diffusers/blob/main/docs/source/en/quantization/overview.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg><!----> <span><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
			
			<script>
				{
					__sveltekit_g37pnb = {
						base: "/docs/diffusers/main/en",
						assets: "/docs/diffusers/main/en"
					};
					const element = document.currentScript.parentElement;
					Promise.all([
						import("/docs/diffusers/main/en/_app/immutable/entry/start.D3LnKZ4R.js"),
						import("/docs/diffusers/main/en/_app/immutable/entry/app.C0rBoMxR.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 313],
							data: [null,null],
							form: null,
							error: null
						});
					});
				}
			</script>
		
Xet Storage Details

Size:: 36.3 kB
Xet hash:: 3efdc0a52508cd60ebff75c789ee7a92cabb25e8d725668b8fd8dfa5a682c542
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.