Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /main /ko /quantization /gguf.html
mishig's picture
mishig
download
raw
21.5 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;GGUF&quot;,&quot;local&quot;:&quot;gguf&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;GGUF에서 최적화된 CUDA 커널 사용&quot;,&quot;local&quot;:&quot;using-optimized-cuda-kernels-with-gguf&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;지원되는 양자화 유형&quot;,&quot;local&quot;:&quot;supported-quantization-types&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;GGUF로 변환&quot;,&quot;local&quot;:&quot;convert-to-gguf&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/diffusers/main/en/_app/immutable/entry/start.vZc-dOUR.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/Bafuik5c.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.B6c3Ml05.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.BQlx092V.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/345.9H87iqJ4.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/B4AMoTAu.js" rel="modulepreload">
<!--12hqa78--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;GGUF&quot;,&quot;local&quot;:&quot;gguf&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Using Optimized CUDA Kernels with GGUF&quot;,&quot;local&quot;:&quot;using-optimized-cuda-kernels-with-gguf&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Supported Quantization Types&quot;,&quot;local&quot;:&quot;supported-quantization-types&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Convert to GGUF&quot;,&quot;local&quot;:&quot;convert-to-gguf&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="gguf" 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="#gguf"><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><!---->GGUF<!----></span></h1><!--]--><!----> <p>GGUF 파일 형식은 일반적으로 <a href="https://github.com/ggerganov/ggml" rel="nofollow">GGML</a>을 사용하여 추론하는 모델을 저장하는 데 사용되며, 다양한 블록 단위 양자화 옵션을 지원합니다. Diffusers는 Model 클래스의 <code>from_single_file</code> 로딩을 통해 GGUF 형식으로 사전 양자화되어 저장된 체크포인트를 로드하는 것을 지원합니다. 현재 Pipeline을 통한 GGUF 체크포인트 로딩은 지원되지 않습니다.</p> <p>다음 예제는 <a href="https://huggingface.co/black-forest-labs/FLUX.1-dev" rel="nofollow">FLUX.1 DEV</a> transformer 모델을 GGUF Q2_K 양자화 변형으로 로드합니다.</p> <p>시작하기 전에 환경에 gguf를 설치하세요</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> 복사됨</div><!----></button><!----></div> <pre class="language-shell "><!---->pip install -U gguf<!----></pre></div><!----> <p>GGUF은 단일 파일 형식이므로, <code>~FromSingleFileMixin.from_single_file</code>를 사용하여 모델을 로드하고 <a href="/docs/diffusers/main/ko/api/quantization#diffusers.GGUFQuantizationConfig">GGUFQuantizationConfig</a>를 전달하세요.</p> <p>GGUF 체크포인트를 사용할 때, 양자화된 가중치는 낮은 메모리 <code>dtype</code>(일반적으로 <code>torch.uint8</code>)로 유지되며, 모델의 각 모듈이 포워드 패스를 수행할 때마다 동적으로 역양자화되어 설정된 <code>compute_dtype</code>으로 캐스트됩니다. <code>GGUFQuantizationConfig</code>를 사용하면 <code>compute_dtype</code>을 설정할 수 있습니다.</p> <p>동적 역양자화에 사용되는 함수들은 <a href="https://github.com/compilade" rel="nofollow">compilade</a>의 원래 <a href="https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/gguf/quants.py" rel="nofollow"><code>numpy</code></a> 구현을 Pytorch로 이식한 <a href="https://github.com/city96/ComfyUI-GGUF" rel="nofollow">city96</a>의 훌륭한 작업을 기반으로 합니다.</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> 복사됨</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, FluxTransformer2DModel, GGUFQuantizationConfig
ckpt_path = (
<span class="hljs-string">&quot;https://huggingface.co/city96/FLUX.1-dev-gguf/blob/main/flux1-dev-Q2_K.gguf&quot;</span>
)
transformer = FluxTransformer2DModel.from_single_file(
ckpt_path,
quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
dtype=torch.bfloat16,
)
pipe = FluxPipeline.from_pretrained(
<span class="hljs-string">&quot;black-forest-labs/FLUX.1-dev&quot;</span>,
transformer=transformer,
dtype=torch.bfloat16,
)
pipe.enable_model_cpu_offload()
prompt = <span class="hljs-string">&quot;A cat holding a sign that says hello world&quot;</span>
image = pipe(prompt, generator=torch.manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;flux-gguf.png&quot;</span>)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="using-optimized-cuda-kernels-with-gguf" 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="#using-optimized-cuda-kernels-with-gguf"><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><!---->GGUF에서 최적화된 CUDA 커널 사용<!----></span></h2><!--]--><!----> <p>최적화된 CUDA 커널은 GGUF 양자화 모델 추론을 약 10% 가속화할 수 있습니다. 이 기능은 <code>torch.cuda.get_device_capability</code>가 7보다 큰 호환 가능한 GPU와 커널 라이브러리가 필요합니다:</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> 복사됨</div><!----></button><!----></div> <pre class="language-shell "><!---->pip install -U kernels<!----></pre></div><!----> <p>설치 후, 최적화된 커널이 사용 가능한 경우 이를 사용하려면 <code>DIFFUSERS_GGUF_CUDA_KERNELS=true</code>를 설정하세요. CUDA 커널은 원래 GGUF 구현과 비교했을 때 미세한 수치적 차이를 유발할 수 있으며, 이로 인해 생성된 이미지에 미묘한 시각적 변이가 발생할 수 있습니다. CUDA 커널 사용을 비활성화하려면 환경 변수 <code>DIFFUSERS_GGUF_CUDA_KERNELS=false</code>를 설정하세요.</p> <p>GGUF 커널은 <a href="https://huggingface.co/Isotr0py/ggml" rel="nofollow"><code>Isotr0py/ggml</code></a> 저장소에서 다운로드되며, 해당 저장소의 게시자는 Hub에서 신뢰할 수 있는 커널 게시자가 아닙니다. 이 커널을 로드하면 Hub에서 코드를 다운로드하고 실행하므로, Diffusers에서는 <code>DIFFUSERS_TRUST_REMOTE_KERNELS=true</code>를 설정하여 명시적으로 허용하도록 요구합니다. 자세한 내용은 <a href="../optimization/attention_backends#trusting-remote-kernels">원격 커널 신뢰</a>를 참조하세요.</p> <!--[1--><h2 class="relative group"><a id="supported-quantization-types" 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="#supported-quantization-types"><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><!---->지원되는 양자화 유형<!----></span></h2><!--]--><!----> <ul><li>BF16</li> <li>Q4_0</li> <li>Q4_1</li> <li>Q5_0</li> <li>Q5_1</li> <li>Q8_0</li> <li>Q2_K</li> <li>Q3_K</li> <li>Q4_K</li> <li>Q5_K</li> <li>Q6_K</li></ul> <!--[1--><h2 class="relative group"><a id="convert-to-gguf" 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="#convert-to-gguf"><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><!---->GGUF로 변환<!----></span></h2><!--]--><!----> <p>아래 Space를 사용하여 Diffusers 체크포인트를 추론을 위한 GGUF 형식으로 변환합니다.
변환 실행:</p> <iframe src="https://diffusers-internal-dev-diffusers-to-gguf.hf.space" frameborder="0" width="850" height="450"></iframe> <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> 복사됨</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> FluxPipeline, FluxTransformer2DModel, GGUFQuantizationConfig
ckpt_path = (
<span class="hljs-string">&quot;https://huggingface.co/sayakpaul/different-lora-from-civitai/blob/main/flux_dev_diffusers-q4_0.gguf&quot;</span>
)
transformer = FluxTransformer2DModel.from_single_file(
ckpt_path,
quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
config=<span class="hljs-string">&quot;black-forest-labs/FLUX.1-dev&quot;</span>,
subfolder=<span class="hljs-string">&quot;transformer&quot;</span>,
dtype=torch.bfloat16,
)
pipe = FluxPipeline.from_pretrained(
<span class="hljs-string">&quot;black-forest-labs/FLUX.1-dev&quot;</span>,
transformer=transformer,
dtype=torch.bfloat16,
)
pipe.enable_model_cpu_offload()
prompt = <span class="hljs-string">&quot;A cat holding a sign that says hello world&quot;</span>
image = pipe(prompt, generator=torch.manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;flux-gguf.png&quot;</span>)<!----></pre></div><!----> <p>Diffusers 형식의 GGUF 체크포인트를 사용할 때는 모델의 <code>config</code> 경로를 반드시 제공해야 합니다. 모델 config가 <code>subfolder</code>에 있는 경우, 해당 경로도 지정해야 합니다.</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/gguf.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_1rjuniz = {
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.vZc-dOUR.js"),
import("/docs/diffusers/main/en/_app/immutable/entry/app.B6c3Ml05.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 345],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
21.5 kB
·
Xet hash:
fe85a66eef5be0ea1c498e7858a7b82182afc4be5283fe1cc11e37f025033470

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