transformers/main/zh/perf_infer_gpu_multi.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;多GPU推理&quot;,&quot;local&quot;:&quot;多gpu推理&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;预期性能提升&quot;,&quot;local&quot;:&quot;预期性能提升&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:1}">
		<link href="/docs/transformers/main/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/entry/start.7a5389c5.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/scheduler.70fef3e7.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/singletons.de8a9de6.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/index.048d9726.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/paths.a6fe27ce.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/entry/app.ac7d4b06.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/preload-helper.77b1b155.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/index.747f74de.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/nodes/0.3408eb2f.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/nodes/52.0159854e.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/CopyLLMTxtMenu.25c10d36.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.04bd7ab0.js">
		<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/CodeBlock.15c43204.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;多GPU推理&quot;,&quot;local&quot;:&quot;多gpu推理&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;预期性能提升&quot;,&quot;local&quot;:&quot;预期性能提升&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div 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>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> </div>  <h1 class="relative group"><a id="多gpu推理" 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="#多gpu推理"><span><svg class="" 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>多GPU推理</span></h1> <p data-svelte-h="svelte-1rnooy8">某些模型现已支持内置的<strong>张量并行</strong>（Tensor Parallelism, TP），并通过 PyTorch 实现。张量并行技术将模型切分到多个 GPU 上，从而支持更大的模型尺寸，并对诸如矩阵乘法等计算任务进行并行化。</p> <p data-svelte-h="svelte-1lcqrkq">要启用张量并行，只需在调用 <code>from_pretrained()</code> 时传递参数 <code>tp_plan=&quot;auto&quot;</code>：</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 class="" 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> Copied</div></button></div> <pre class="language-python "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> os
<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForCausalLM, AutoTokenizer

model_id = <span class="hljs-string">&quot;meta-llama/Meta-Llama-3-8B-Instruct&quot;</span>

<span class="hljs-comment"># 初始化分布式环境</span>
rank = <span class="hljs-built_in">int</span>(os.environ[<span class="hljs-string">&quot;RANK&quot;</span>])
device = torch.device(<span class="hljs-string">f&quot;cuda:<span class="hljs-subst">{rank}</span>&quot;</span>)
torch.cuda.set_device(device)
torch.distributed.init_process_group(<span class="hljs-string">&quot;nccl&quot;</span>, device_id=device)

<span class="hljs-comment"># 获取支持张量并行的模型</span>
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    tp_plan=<span class="hljs-string">&quot;auto&quot;</span>,
)

<span class="hljs-comment"># 准备输入tokens</span>
tokenizer = AutoTokenizer.from_pretrained(model_id)
prompt = <span class="hljs-string">&quot;Can I help&quot;</span>
inputs = tokenizer(prompt, return_tensors=<span class="hljs-string">&quot;pt&quot;</span>).input_ids.to(device)

<span class="hljs-comment"># 分布式运行</span>
outputs = model(inputs)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1u51d1q">您可以使用 <code>torchrun</code> 命令启动上述脚本，多进程模式会自动将每个进程映射到一张 GPU：</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 class="" 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> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->torchrun --nproc-per-<span class="hljs-keyword">node</span> <span class="hljs-title">4</span> demo.py<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-15hz8rz">目前，PyTorch 张量并行支持以下模型：</p> <ul data-svelte-h="svelte-wihcs3"><li><a href="https://huggingface.co/docs/transformers/model_doc/llama#transformers.LlamaModel" rel="nofollow">Llama</a></li></ul> <p data-svelte-h="svelte-dhflz7">如果您希望对其他模型添加张量并行支持，可以通过提交 GitHub Issue 或 Pull Request 来提出请求。</p>  <h3 class="relative group"><a id="预期性能提升" 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="#预期性能提升"><span><svg class="" 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>预期性能提升</span></h3> <p data-svelte-h="svelte-sjssgg">对于推理场景（尤其是处理大批量或长序列的输入），张量并行可以显著提升计算速度。</p> <p data-svelte-h="svelte-1gd4c5g">以下是 <a href="https://huggingface.co/docs/transformers/model_doc/llama#transformers.LlamaModel" rel="nofollow">Llama</a> 模型在序列长度为 512 且不同批量大小情况下的单次前向推理的预期加速效果：</p> <div style="text-align: center" data-svelte-h="svelte-lg3kfi"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/Meta-Llama-3-8B-Instruct%2C%20seqlen%20%3D%20512%2C%20python%2C%20w_%20compile.png"></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/zh/perf_infer_gpu_multi.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 data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_zpy4e4 = {
						assets: "/docs/transformers/main/zh",
						base: "/docs/transformers/main/zh",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/transformers/main/zh/_app/immutable/entry/start.7a5389c5.js"),
						import("/docs/transformers/main/zh/_app/immutable/entry/app.ac7d4b06.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 52],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>