Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"DDP Communication Hooks","local":"ddp-communication-hooks","sections":[{"title":"FP16 Compression Hook","local":"fp16-compression-hook","sections":[{"title":"BF16 Compression Hook","local":"bf16-compression-hook","sections":[],"depth":3},{"title":"PowerSGD Hook","local":"powersgd-hook","sections":[],"depth":3}],"depth":2},{"title":"DDP Communication Hooks utilities","local":"ddp-communication-hooks-utilities","sections":[{"title":"comm_wrapper","local":"commwrapper","sections":[],"depth":3},{"title":"comm_state_option","local":"commstateoption","sections":[],"depth":3}],"depth":2}],"depth":1}"> | |
| <link href="/docs/accelerate/pr_4021/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/entry/start.8a49e72b.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/scheduler.b9285784.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/singletons.7547c222.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/index.6d423e5c.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/paths.d42c9205.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/entry/app.1df4d18e.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/preload-helper.b0bd19d1.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/index.26bc89a1.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/nodes/0.0e7c56e8.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/nodes/41.1a67c953.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/Tip.e4eba3d6.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.7a0ae628.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/CodeBlock.844ff9c3.js"> | |
| <link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/HfOption.76c7ca3e.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"DDP Communication Hooks","local":"ddp-communication-hooks","sections":[{"title":"FP16 Compression Hook","local":"fp16-compression-hook","sections":[{"title":"BF16 Compression Hook","local":"bf16-compression-hook","sections":[],"depth":3},{"title":"PowerSGD Hook","local":"powersgd-hook","sections":[],"depth":3}],"depth":2},{"title":"DDP Communication Hooks utilities","local":"ddp-communication-hooks-utilities","sections":[{"title":"comm_wrapper","local":"commwrapper","sections":[],"depth":3},{"title":"comm_state_option","local":"commstateoption","sections":[],"depth":3}],"depth":2}],"depth":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="ddp-communication-hooks" 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="#ddp-communication-hooks"><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>DDP Communication Hooks</span></h1> <p data-svelte-h="svelte-x6tyko">Distributed Data Parallel (DDP) communication hooks provide a generic interface to control how gradients are communicated across workers by overriding the vanilla allreduce in <code>DistributedDataParallel</code>. A few built-in communication hooks are provided, and users can easily apply any of these hooks to optimize communication.</p> <ul data-svelte-h="svelte-zxp3oz"><li><strong>FP16 Compression Hook</strong>: Compresses gradients by casting them to half-precision floating-point format (<code>torch.float16</code>), reducing communication overhead.</li> <li><strong>BF16 Compression Hook</strong>: Similar to FP16, but uses the Brain Floating Point format (<code>torch.bfloat16</code>), which can be more efficient on certain hardware.</li> <li><strong>PowerSGD Hook</strong>: An advanced gradient compression algorithm that provides high compression rates and can accelerate bandwidth-bound distributed training.</li></ul> <p data-svelte-h="svelte-10ve3hd">In this tutorial, you will see how to quickly set up DDP communication hooks and perform training with the utilities provided in Accelerate, which can be as simple as adding just one new line of code! This demonstrates how to use DDP communication hooks to optimize gradient communication in distributed training with the Accelerate library.</p> <h2 class="relative group"><a id="fp16-compression-hook" 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="#fp16-compression-hook"><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>FP16 Compression Hook</span></h2> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white">PyTorch </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm">Accelerate </div></div> <div class="language-select"><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 --><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">from</span> torch.nn.parallel <span class="hljs-keyword">import</span> DistributedDataParallel <span class="hljs-keyword">as</span> DDP | |
| <span class="hljs-keyword">from</span> torch.distributed.algorithms.ddp_comm_hooks <span class="hljs-keyword">import</span> default_hooks | |
| <span class="hljs-keyword">from</span> accelerate.test_utils.testing <span class="hljs-keyword">import</span> get_backend | |
| device_type, _, _ = get_backend() | |
| device_id = <span class="hljs-built_in">getattr</span>(torch, device_type, torch.cuda).current_device() | |
| <span class="hljs-keyword">class</span> <span class="hljs-title class_">MyModel</span>(torch.nn.Module): | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">__init__</span>(<span class="hljs-params">self</span>): | |
| <span class="hljs-built_in">super</span>().__init__() | |
| self.layer = torch.nn.Linear(<span class="hljs-number">10</span>, <span class="hljs-number">10</span>) | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">forward</span>(<span class="hljs-params">self, x</span>): | |
| <span class="hljs-keyword">return</span> self.layer(x) | |
| model = MyModel() | |
| model = DDP(model, device_ids=[device_id]) | |
| model.register_comm_hook(state=<span class="hljs-literal">None</span>, hook=default_hooks.fp16_compress_hook) | |
| <span class="hljs-comment"># Training loop</span> | |
| <span class="hljs-keyword">for</span> data, targets <span class="hljs-keyword">in</span> data_loader: | |
| outputs = model(data) | |
| loss = criterion(outputs, targets) | |
| loss.backward() | |
| optimizer.step() | |
| optimizer.zero_grad()<!-- HTML_TAG_END --></pre></div> </div> <h3 class="relative group"><a id="bf16-compression-hook" 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="#bf16-compression-hook"><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>BF16 Compression Hook</span></h3> <blockquote class="warning"><p data-svelte-h="svelte-1s0p8uc">BF16 Compression Hook API is experimental, and it requires NCCL version later than 2.9.6.</p></blockquote> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white">PyTorch </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm">Accelerate </div></div> <div class="language-select"><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 --><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">from</span> torch.nn.parallel <span class="hljs-keyword">import</span> DistributedDataParallel <span class="hljs-keyword">as</span> DDP | |
| <span class="hljs-keyword">from</span> torch.distributed.algorithms.ddp_comm_hooks <span class="hljs-keyword">import</span> default_hooks | |
| <span class="hljs-keyword">from</span> accelerate.test_utils.testing <span class="hljs-keyword">import</span> get_backend | |
| device_type, _, _ = get_backend() | |
| device_id = <span class="hljs-built_in">getattr</span>(torch, device_type, torch.cuda).current_device() | |
| <span class="hljs-keyword">class</span> <span class="hljs-title class_">MyModel</span>(torch.nn.Module): | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">__init__</span>(<span class="hljs-params">self</span>): | |
| <span class="hljs-built_in">super</span>().__init__() | |
| self.layer = torch.nn.Linear(<span class="hljs-number">10</span>, <span class="hljs-number">10</span>) | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">forward</span>(<span class="hljs-params">self, x</span>): | |
| <span class="hljs-keyword">return</span> self.layer(x) | |
| model = MyModel() | |
| model = DDP(model, device_ids=[device_id]) | |
| model.register_comm_hook(state=<span class="hljs-literal">None</span>, hook=default_hooks.bf16_compress_hook) | |
| <span class="hljs-comment"># Training loop</span> | |
| <span class="hljs-keyword">for</span> data, targets <span class="hljs-keyword">in</span> data_loader: | |
| outputs = model(data) | |
| loss = criterion(outputs, targets) | |
| loss.backward() | |
| optimizer.step() | |
| optimizer.zero_grad()<!-- HTML_TAG_END --></pre></div> </div> <h3 class="relative group"><a id="powersgd-hook" 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="#powersgd-hook"><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>PowerSGD Hook</span></h3> <blockquote class="warning"><p data-svelte-h="svelte-1f2etf0">PowerSGD typically requires extra memory of the same size as the model’s gradients to enable error feedback, which can compensate for biased compressed communication and improve accuracy.</p></blockquote> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white">PyTorch </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm">Accelerate </div></div> <div class="language-select"><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 --><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">from</span> torch.nn.parallel <span class="hljs-keyword">import</span> DistributedDataParallel <span class="hljs-keyword">as</span> DDP | |
| <span class="hljs-keyword">from</span> torch.distributed.algorithms.ddp_comm_hooks <span class="hljs-keyword">import</span> powerSGD_hook | |
| <span class="hljs-keyword">from</span> accelerate.test_utils.testing <span class="hljs-keyword">import</span> get_backend | |
| device_type, _, _ = get_backend() | |
| device_id = <span class="hljs-built_in">getattr</span>(torch, device_type, torch.cuda).current_device() | |
| <span class="hljs-keyword">class</span> <span class="hljs-title class_">MyModel</span>(torch.nn.Module): | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">__init__</span>(<span class="hljs-params">self</span>): | |
| <span class="hljs-built_in">super</span>().__init__() | |
| self.layer = torch.nn.Linear(<span class="hljs-number">10</span>, <span class="hljs-number">10</span>) | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">forward</span>(<span class="hljs-params">self, x</span>): | |
| <span class="hljs-keyword">return</span> self.layer(x) | |
| model = MyModel() | |
| model = DDP(model, device_ids=[device_id]) | |
| state = powerSGD_hook.PowerSGDState(process_group=<span class="hljs-literal">None</span>) | |
| model.register_comm_hook(state=state, hook=powerSGD_hook.powerSGD_hook) | |
| <span class="hljs-comment"># Training loop</span> | |
| <span class="hljs-keyword">for</span> data, targets <span class="hljs-keyword">in</span> data_loader: | |
| outputs = model(data) | |
| loss = criterion(outputs, targets) | |
| loss.backward() | |
| optimizer.step() | |
| optimizer.zero_grad()<!-- HTML_TAG_END --></pre></div> </div> <h2 class="relative group"><a id="ddp-communication-hooks-utilities" 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="#ddp-communication-hooks-utilities"><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>DDP Communication Hooks utilities</span></h2> <p data-svelte-h="svelte-1nbipsx">There are two additional utilities for supporting optional functionalities with the communication hooks.</p> <h3 class="relative group"><a id="commwrapper" 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="#commwrapper"><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>comm_wrapper</span></h3> <p data-svelte-h="svelte-oi3r9p"><code>comm_wrapper</code> is an option to wrap a communication hook with additional functionality. For example, it can be used to combine FP16 compression with other communication strategies. Currently supported wrappers are <code>no</code>, <code>fp16</code>, and <code>bf16</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=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> accelerate <span class="hljs-keyword">import</span> Accelerator, DDPCommunicationHookType, DistributedDataParallelKwargs | |
| <span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">class</span> <span class="hljs-title class_">MyModel</span>(torch.nn.Module): | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">__init__</span>(<span class="hljs-params">self</span>): | |
| <span class="hljs-built_in">super</span>().__init__() | |
| self.layer = torch.nn.Linear(<span class="hljs-number">10</span>, <span class="hljs-number">10</span>) | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">forward</span>(<span class="hljs-params">self, x</span>): | |
| <span class="hljs-keyword">return</span> self.layer(x) | |
| <span class="hljs-comment"># DDP Communication Hook setup</span> | |
| ddp_kwargs = DistributedDataParallelKwargs( | |
| comm_hook=DDPCommunicationHookType.POWER_SGD, | |
| comm_wrapper=DDPCommunicationHookType.FP16 | |
| ) | |
| accelerator = Accelerator(kwargs_handlers=[ddp_kwargs]) | |
| model = MyModel() | |
| optimizer = torch.optim.Adam(model.parameters()) | |
| data_loader = DataLoader(dataset, batch_size=<span class="hljs-number">16</span>) | |
| model, optimizer, data_loader = accelerator.prepare(model, optimizer, data_loader) | |
| <span class="hljs-comment"># Training loop</span> | |
| <span class="hljs-keyword">for</span> data, targets <span class="hljs-keyword">in</span> data_loader: | |
| outputs = model(data) | |
| loss = criterion(outputs, targets) | |
| accelerator.backward(loss) | |
| optimizer.step() | |
| optimizer.zero_grad()<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="commstateoption" 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="#commstateoption"><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>comm_state_option</span></h3> <p data-svelte-h="svelte-1igm2b3"><code>comm_state_option</code> allows you to pass additional state information required by certain communication hooks. This is particularly useful for stateful hooks like <code>PowerSGD</code>, which require maintaining hyperparameters and internal states across training steps. Below is an example showcasing the use of <code>comm_state_option</code> with the <code>PowerSGD</code> hook.</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 --><span class="hljs-keyword">from</span> accelerate <span class="hljs-keyword">import</span> Accelerator, DDPCommunicationHookType, DistributedDataParallelKwargs | |
| <span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">class</span> <span class="hljs-title class_">MyModel</span>(torch.nn.Module): | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">__init__</span>(<span class="hljs-params">self</span>): | |
| <span class="hljs-built_in">super</span>().__init__() | |
| self.layer = torch.nn.Linear(<span class="hljs-number">10</span>, <span class="hljs-number">10</span>) | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">forward</span>(<span class="hljs-params">self, x</span>): | |
| <span class="hljs-keyword">return</span> self.layer(x) | |
| <span class="hljs-comment"># DDP Communication Hook setup</span> | |
| ddp_kwargs = DistributedDataParallelKwargs( | |
| comm_hook=DDPCommunicationHookType.POWER_SGD, | |
| comm_state_option={<span class="hljs-string">"matrix_approximation_rank"</span>: <span class="hljs-number">2</span>} | |
| ) | |
| accelerator = Accelerator(kwargs_handlers=[ddp_kwargs]) | |
| model = MyModel() | |
| optimizer = torch.optim.Adam(model.parameters()) | |
| data_loader = DataLoader(dataset, batch_size=<span class="hljs-number">16</span>) | |
| model, optimizer, data_loader = accelerator.prepare(model, optimizer, data_loader) | |
| <span class="hljs-comment"># Training loop</span> | |
| <span class="hljs-keyword">for</span> data, targets <span class="hljs-keyword">in</span> data_loader: | |
| outputs = model(data) | |
| loss = criterion(outputs, targets) | |
| accelerator.backward(loss) | |
| optimizer.step() | |
| optimizer.zero_grad()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ll6vn">For more advanced usage and additional hooks, refer to the <a href="https://pytorch.org/docs/stable/ddp_comm_hooks.html" rel="nofollow">PyTorch DDP Communication Hooks documentation</a>.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/accelerate/blob/main/docs/source/usage_guides/ddp_comm_hook.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_1q7nz6m = { | |
| assets: "/docs/accelerate/pr_4021/en", | |
| base: "/docs/accelerate/pr_4021/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/accelerate/pr_4021/en/_app/immutable/entry/start.8a49e72b.js"), | |
| import("/docs/accelerate/pr_4021/en/_app/immutable/entry/app.1df4d18e.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 41], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 33.6 kB
- Xet hash:
- 6dc4dbf1807524475fce30fd60ac6002e75281e5b4f7220fd0411de426fd3f5f
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.