Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /v0.43.0 /zh /quantization /bfl.html
mishig's picture
mishig
download
raw
13.9 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;BFL（fp8r / nvfp4）&quot;,&quot;local&quot;:&quot;bfl-fp8r--nvfp4&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;内核&quot;,&quot;local&quot;:&quot;kernels&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/diffusers/main/en/_app/immutable/entry/start.0S0_iEoG.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/I9eooN77.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/Bupkjr9f.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/entry/app.CPdOxCbw.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/CyvZ3FS5.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/l0QnnOED.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.DteTvmQZ.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/CoSrdQax.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/nodes/351.Cu90JRCw.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DSPDl1gz.js" rel="modulepreload">
<!--7gq4hb--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;BFL (fp8r / nvfp4)&quot;,&quot;local&quot;:&quot;bfl-fp8r--nvfp4&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Kernels&quot;,&quot;local&quot;:&quot;kernels&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="bfl-fp8r--nvfp4" 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="#bfl-fp8r--nvfp4"><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><!---->BFL（fp8r / nvfp4）<!----></span></h1><!--]--><!----> <p><a href="https://huggingface.co/black-forest-labs" rel="nofollow">Black Forest Labs</a> 为其 <a href="../api/pipelines/flux3">Flux3</a> 模型提供了两种量化方案，以单文件检查点的形式与原始 bf16 权重一同存放：</p> <ul><li><code>fp8r</code>：行级 FP8。每个量化线性层存储一个 E4M3 格式的 <code>weight</code> 和一个 fp32 格式的按行 <code>weight_scale</code>。激活值在运行时按行量化为 E4M3。</li> <li><code>nvfp4</code>：<a href="https://github.com/NVIDIA/Model-Optimizer" rel="nofollow">ModelOpt</a> 布局下的 NVFP4。每个量化线性层存储打包的 E2M1 <code>weight</code>（每字节两个值）、16 个 E4M3 块缩放因子（<code>weight_scale</code>）、一个全局 fp32 <code>weight_scale_2</code>，以及一个经过校准的 fp32 激活缩放因子 <code>input_scale</code>。</li></ul> <p>Diffusers 通过 <code>~FromSingleFileMixin.from_single_file</code> 加载两者，并使用 <a href="/docs/diffusers/v0.43.0/zh/api/quantization#diffusers.BFLQuantizationConfig">BFLQuantizationConfig</a>。量化方案从检查点中读取，因此相同的配置适用于任一文件。仅支持加载预量化检查点，不支持在流水线级别加载。</p> <p>以下示例加载 <a href="https://huggingface.co/black-forest-labs/flux-3-image-klein-base" rel="nofollow">FLUX 3 Image Klein Base</a> 的 <code>fp8r</code> 检查点，该检查点位于模型仓库的 <code>variants/fp8r/model.safetensors</code> 路径下。传入 <code>config</code> 以从该仓库的 Diffusers 文件夹中读取模型配置，然后按名称加载其他组件（参见 <a href="../api/pipelines/flux3#single-file-loading">单文件加载</a>）。</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> 已复制</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> BFLQuantizationConfig, Flux3Transformer2DModel, ModularPipeline
ckpt_path = <span class="hljs-string">&quot;https://huggingface.co/black-forest-labs/flux-3-image-klein-base/blob/main/variants/fp8r/model.safetensors&quot;</span>
transformer = Flux3Transformer2DModel.from_single_file(
ckpt_path,
config=<span class="hljs-string">&quot;black-forest-labs/flux-3-image-klein-base&quot;</span>,
subfolder=<span class="hljs-string">&quot;transformer&quot;</span>,
quantization_config=BFLQuantizationConfig(compute_dtype=torch.bfloat16),
dtype=torch.bfloat16,
)
pipe = ModularPipeline.from_pretrained(<span class="hljs-string">&quot;black-forest-labs/flux-3-image-klein-base&quot;</span>)
pipe.load_components(dtype=torch.bfloat16)
pipe.update_components(transformer=transformer)
pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)
prompt = <span class="hljs-string">&quot;A wide-angle wildlife photograph of a red fox standing alert in a snow-covered forest clearing at golden hour.&quot;</span>
image = pipe(prompt=prompt, generator=torch.Generator().manual_seed(<span class="hljs-number">0</span>), output=<span class="hljs-string">&quot;images&quot;</span>)[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;flux3-klein-base-fp8r.png&quot;</span>)<!----></pre></div><!----> <p>将 <code>variants/fp8r</code> 替换为 <code>variants/nvfp4</code> 以加载 <code>nvfp4</code> 变体。步数蒸馏版 <a href="https://huggingface.co/black-forest-labs/flux-3-image-klein" rel="nofollow">FLUX 3 Image Klein</a> 提供相同的两个变体；加载时，将其仓库 id 作为 <code>config</code> 和 pipeline 传入。</p> <!--[1--><h2 class="relative group"><a id="kernels" 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="#kernels"><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><!---->内核<!----></span></h2><!--]--><!----> <p>量化后的权重保持在其低精度存储 dtype 中。具体执行哪种 GEMM 取决于设备：</p> <table><thead><tr><th>方案</th><th>融合内核</th><th>要求</th></tr></thead><tbody><tr><td><code>fp8r</code></td><td>使用行级缩放的 <code>torch._scaled_mm</code></td><td>计算能力为 8.9 或更高的 CUDA GPU</td></tr><tr><td><code>nvfp4</code></td><td><code>flashinfer.mm_fp4</code>（CUTLASS）配合 <code>flashinfer.nvfp4_quantize</code> 用于激活值</td><td>Blackwell GPU（计算能力 10.0 或更高）、包含 <code>nvcc</code> 的 CUDA 工具包，以及版本相同的 <code>flashinfer-python</code> 和 <code>flashinfer-cubin</code></td></tr></tbody></table> <p>请同时安装相同版本的两个 FlashInfer 软件包，例如 <code>pip install flashinfer-python==0.6.13 flashinfer-cubin==0.6.13</code>。<code>flashinfer-cubin</code> 的发布版本可能会落后于 <code>flashinfer-python</code>，当两个包的版本不一致时，FlashInfer 会拒绝导入。</p> <p>FlashInfer 在首次使用时，会使用当前环境的 CUDA 工具包编译其 NVFP4 内核，并根据可见的 GPU（或当设置了 <code>FLASHINFER_CUDA_ARCH_LIST</code> 时，根据该变量）选择目标架构。消费级和工作站 Blackwell GPU（计算能力 12.0）需要 12.9 或更高版本的 CUDA 工具包。如果使用较旧的工具包，FlashInfer 将找不到符合条件的架构，首次 NVFP4 调用会因 <code>FlashInfer requires GPUs with sm75 or higher</code> 而失败。</p> <p>在其他任何设备上，权重会在每次前向传播中反量化为 <code>compute_dtype</code>，该层作为常规线性层运行。在这种情况下，激活值不会被量化，因此输出与融合内核的结果略有差异。</p> <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/bfl.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_1qsdbwf = {
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.0S0_iEoG.js"),
import("/docs/diffusers/main/en/_app/immutable/entry/app.CPdOxCbw.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 351],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
13.9 kB
·
Xet hash:
6dd828f31ddd9e920c680dc3f02ee5446d47835b3f2d4077099c857ce6f54479

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.