Buckets:

hf-doc-build
/

doc

Files
xet
hf-doc-build/doc / diffusers /main /ja /optimization /tpu.html
mishig
1 day ago
download
raw
26.8 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Google TPU&quot;,&quot;local&quot;:&quot;google-tpu&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Eager モード&quot;,&quot;local&quot;:&quot;eager-mode&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;コンパイルモード&quot;,&quot;local&quot;:&quot;compiled-mode&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;テンソル並列&quot;,&quot;local&quot;:&quot;tensor-parallelism&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/311.C19KkVwx.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/bKdwVYpU.js" rel="modulepreload">
		<!--vjbfci--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Google TPU&quot;,&quot;local&quot;:&quot;google-tpu&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Eager mode&quot;,&quot;local&quot;:&quot;eager-mode&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Compiled mode&quot;,&quot;local&quot;:&quot;compiled-mode&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Tensor parallelism&quot;,&quot;local&quot;:&quot;tensor-parallelism&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="google-tpu" 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="#google-tpu"><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><!---->Google TPU<!----></span></h1><!--]--><!----> <p>Tensor Processing Units (TPU) は、Google による機械学習アクセラレーターであり、Cloud TPU (v6e、v7x) として利用できます。
Diffusers は、TPU 向けの PyTorch バックエンドである <a href="https://github.com/google-pytorch/torch_tpu/" rel="nofollow">TorchTPU</a> を通じて TPUs 上で動作し、コードの修正は最小限で済みます。</p> <p>3つの実行モードが利用可能です:</p> <table><thead><tr><th>モード</th><th>定数</th><th>有効化する方法</th><th>注記</th></tr></thead><tbody><tr><td>厳密な eager（デフォルト）</td><td><code>EagerMode.DEFER_NEVER</code></td><td><code>pipe.to("tpu")</code></td><td>1回ずつディスパッチされる非同期のオペレーション</td></tr><tr><td>最適化された eager</td><td><code>EagerMode.DEFER_AND_FUSE</code></td><td><code>TORCH_TPU_DEFER_AND_FUSE=1</code></td><td>操作がデフェラされ、より大きなグラフに融合されます。厳密なイージアモードよりも高速ですが、コンパイル時間は長くなります。</td></tr><tr><td>コンパイル</td><td>—</td><td><code>torch.compile(module, backend="tpu")</code></td><td><code>TpuBackend</code> による AOT コンパイル</td></tr></tbody></table> <p><a href="https://github.com/google-pytorch/torch_tpu/" rel="nofollow">TorchTPU インストールガイド</a>に従ってください。インストールが完了すると、<code>import torch</code> を実行するだけで自動的に読み込まれ、<code>"tpu"</code> デバイスが登録されるため、<code>pipe.to("tpu")</code> に変更するだけで対応できます。バックエンドの自動読み込みを <code>TORCH_DEVICE_BACKEND_AUTOLOAD=0</code> で無効化している場合のみ、<code>import torch_tpu</code> を追加してください。</p> <!--[1--><h2 class="relative group"><a id="eager-mode" 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="#eager-mode"><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><!---->Eager モード<!----></span></h2><!--]--><!----> <p>FLUX.1-schnell は単一の v6e チップに一度には収まらないため、<a href="/docs/diffusers/main/ja/api/pipelines/overview#diffusers.DiffusionPipeline.enable_model_cpu_offload">enable_model_cpu_offload()</a> を使用して、各モデルを実行している間のみ TPU に移動させます。<code>"tpu"</code> デバイスは自動的に検出されます。</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-python "><!----><span class="hljs-keyword">import</span> torch

<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> FluxPipeline

pipe = FluxPipeline.from_pretrained(<span class="hljs-string">&quot;black-forest-labs/FLUX.1-schnell&quot;</span>, dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

image = pipe(
    prompt=<span class="hljs-string">&quot;a golden retriever surfing a wave, photorealistic&quot;</span>,
    height=<span class="hljs-number">1024</span>,
    width=<span class="hljs-number">1024</span>,
    num_inference_steps=<span class="hljs-number">4</span>,
    guidance_scale=<span class="hljs-number">0.0</span>,
).images[<span class="hljs-number">0</span>]

image.save(<span class="hljs-string">&quot;output.png&quot;</span>)<!----></pre></div><!----> <p>モデルが1つのチップに収まらない場合、または複数のチップを所有していてレイテンシを下げたい場合は、代わりにモデルをチップ間でシャードしてください。<a href="#tensor-parallelism">テンソル並列</a>セクションを参照してください。</p> <!--[1--><h2 class="relative group"><a id="compiled-mode" 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="#compiled-mode"><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><!---->コンパイルモード<!----></span></h2><!--]--><!----> <p>TorchTPU は <code>"tpu"</code> を <code>torch.compile</code> のバックエンド名として登録します（内部では <code>TpuBackend</code> として実装されています）。そのため、コンポーネントは他の <code>torch.compile</code> ターゲットと同様にコンパイルされます。最初の呼び出し（ウォームアップ）はコンパイルを行うため遅くなりますが、同じ形状での後続の呼び出しではコンパイル済みグラフが再利用されます。</p> <blockquote class="important"><p>TorchTPU は <strong>静的な形状</strong>を必要とするため、<code>dynamic=False</code> を渡してください。新しい <code>height</code> または <code>width</code> が指定されると、その形状に対して一度だけ再コンパイルが行われます。すでに確認済みの形状は再利用されます。<code>num_inference_steps</code> を変更しても再コンパイルは行われません。</p></blockquote> <p>パイプライン全体が1つのチップに収まる場合は、TPUに移動してトランスフォーマー全体をコンパイルします。Stable Diffusion 3.5 Medium（bf16で約15GB）は、単一のv6eチップに収まります。</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-python "><!----><span class="hljs-keyword">import</span> torch

<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained(<span class="hljs-string">&quot;stabilityai/stable-diffusion-3.5-medium&quot;</span>, dtype=torch.bfloat16)
pipe.to(<span class="hljs-string">&quot;tpu&quot;</span>)
pipe.transformer.<span class="hljs-built_in">compile</span>(backend=<span class="hljs-string">&quot;tpu&quot;</span>, fullgraph=<span class="hljs-literal">True</span>, dynamic=<span class="hljs-literal">False</span>)

<span class="hljs-comment"># Warmup — triggers static graph compilation.</span>
pipe(prompt=<span class="hljs-string">&quot;warmup&quot;</span>, height=<span class="hljs-number">1024</span>, width=<span class="hljs-number">1024</span>, num_inference_steps=<span class="hljs-number">40</span>, guidance_scale=<span class="hljs-number">4.5</span>)

<span class="hljs-comment"># Later calls with the same shapes reuse the compiled graph.</span>
image = pipe(
    prompt=<span class="hljs-string">&quot;a golden retriever surfing a wave, photorealistic&quot;</span>,
    height=<span class="hljs-number">1024</span>,
    width=<span class="hljs-number">1024</span>,
    num_inference_steps=<span class="hljs-number">40</span>,
    guidance_scale=<span class="hljs-number">4.5</span>,
).images[<span class="hljs-number">0</span>]

image.save(<span class="hljs-string">&quot;output.png&quot;</span>)<!----></pre></div><!----> <p>パイプラインが1つのチップに収まらない場合:</p> <ul><li>複数のチップを使用する場合は、代わりに<a href="#tensor-parallelism">テンソル並列</a>でシャード化します。すべてがTPU上に保持され、<code>pipe.transformer.compile(...)</code>はシャード化されたtransformerでも同じように動作します。</li> <li><a href="/docs/diffusers/main/ja/api/pipelines/overview#diffusers.DiffusionPipeline.enable_model_cpu_offload">enable_model_cpu_offload()</a> を使用すると、オフロードフックは <code>torch.compile</code> によってトレースできません。代わりに、<code>pipe.transformer.compile_repeated_blocks(backend="tpu", fullgraph=True, dynamic=False)</code> を使用して、transformer の繰り返しブロックのみをコンパイルしてください。</li></ul> <!--[1--><h2 class="relative group"><a id="tensor-parallelism" 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="#tensor-parallelism"><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><!---->テンソル並列<!----></span></h2><!--]--><!----> <p>1つのチップに収まらないほど大きなモデルを複数のチップに分割します。FLUX.2-devのテキストエンコーダー（約48GB）とトランスフォーマー（約64GB）はそれぞれ1つのチップの容量を超えているため、以下の例では両方をシャードしています。</p> <ul><li><a href="/docs/diffusers/main/ja/api/parallel#diffusers.TensorParallelConfig">TensorParallelConfig</a> を使用した transformer を、<a href="/docs/diffusers/main/ja/api/models/overview#diffusers.ModelMixin.from_pretrained">from_pretrained()</a> の <code>parallel_config</code> 引数に渡します。各ランクは、シャード化された重みのうち自分のスライスのみを読み取るため、完全なモデルはメモリ上に展開されません。TP の一般的な詳細（<code>_tp_plan</code>、colwise/rowwise）については、<a href="./tensor_parallelism">テンソル並列性</a>ガイドを参照してください。</li> <li>Transformers 独自の <a href="https://huggingface.co/docs/transformers/perf_infer_gpu_multi" rel="nofollow">テンソル並列性</a> を使用してテキストエンコーダーを構成し、<a href="https://huggingface.co/docs/transformers/main/en/expert_parallelism#transformers.DistributedConfig" rel="nofollow">DistributedConfig</a> と同じメッシュを渡します。</li></ul> <p>TPU では、<code>backend="tpu_dist"</code> を指定してプロセスグループを初期化し、<code>DeviceMesh("tpu", ...)</code> でメッシュを構築します。</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-python "><!----><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">import</span> torch.distributed <span class="hljs-keyword">as</span> dist
<span class="hljs-keyword">from</span> torch.distributed.device_mesh <span class="hljs-keyword">import</span> DeviceMesh
<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DistributedConfig, Mistral3ForConditionalGeneration

<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> Flux2Pipeline, Flux2Transformer2DModel, TensorParallelConfig

dist.init_process_group(backend=<span class="hljs-string">&quot;tpu_dist&quot;</span>)
mesh = DeviceMesh(<span class="hljs-string">&quot;tpu&quot;</span>, <span class="hljs-built_in">list</span>(<span class="hljs-built_in">range</span>(dist.get_world_size())))

repo_id = <span class="hljs-string">&quot;black-forest-labs/FLUX.2-dev&quot;</span>
text_encoder = Mistral3ForConditionalGeneration.from_pretrained(
    repo_id,
    subfolder=<span class="hljs-string">&quot;text_encoder&quot;</span>,
    dtype=torch.bfloat16,
    distributed_config=DistributedConfig(tp_plan=<span class="hljs-string">&quot;auto&quot;</span>),
    device_mesh=mesh,
)
transformer = Flux2Transformer2DModel.from_pretrained(
    repo_id, subfolder=<span class="hljs-string">&quot;transformer&quot;</span>, dtype=torch.bfloat16, parallel_config=TensorParallelConfig(mesh=mesh)
)
pipe = Flux2Pipeline.from_pretrained(
    repo_id, text_encoder=text_encoder, transformer=transformer, dtype=torch.bfloat16
)
pipe.vae.to(<span class="hljs-string">&quot;tpu&quot;</span>)

image = pipe(
    prompt=<span class="hljs-string">&quot;a golden retriever surfing a wave, photorealistic&quot;</span>,
    num_inference_steps=<span class="hljs-number">28</span>,
    generator=torch.Generator(<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(<span class="hljs-number">0</span>),
).images[<span class="hljs-number">0</span>]
<span class="hljs-keyword">if</span> dist.get_rank() == <span class="hljs-number">0</span>:
    image.save(<span class="hljs-string">&quot;output.png&quot;</span>)<!----></pre></div><!----> <p>チップごとに1つのプロセスを起動します。ホスト上のすべてのTPUチップを使用するには、<code>--nproc_per_node</code>を設定してください。</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-bash "><!----><span class="hljs-built_in">eval</span> $(python -m torch_tpu._internal.distributed.launchers.singlehost_wrapper | sed <span class="hljs-string">&#x27;s/^/export /&#x27;</span>)
torchrun --nproc_per_node=8 flux2_tp.py<!----></pre></div><!----> <blockquote class="warning"><p>上記の起動コマンドは、安定した API ではなく TorchTPU の内部モジュール（<code>torch_tpu._internal</code>）を使用しており、将来の TorchTPU リリースで変更される予定です。マルチチップジョブを起動する最新のやり方については、<a href="https://github.com/google-pytorch/torch_tpu/" rel="nofollow">TorchTPU リポジトリ</a>を確認してください。</p></blockquote> <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/optimization/tpu.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, 311],
							data: [null,null],
							form: null,
							error: null
						});
					});
				}
			</script>
		
Xet Storage Details

Size:: 26.8 kB
Xet hash:: 6c339c51f1368b80bf63964b42d7d2b45d6d2df92b817748918d745b271dfdfb
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.