Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / transformers /pr_36839 /en /quantization /awq.html
rtrm's picture
rtrm
download
raw
35.5 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;AWQ&quot;,&quot;local&quot;:&quot;awq&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Fused modules&quot;,&quot;local&quot;:&quot;fused-modules&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ExLlamaV2&quot;,&quot;local&quot;:&quot;exllamav2&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;CPU&quot;,&quot;local&quot;:&quot;cpu&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Resources&quot;,&quot;local&quot;:&quot;resources&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/transformers/pr_36839/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/entry/start.6be8d590.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/scheduler.01eeda35.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/singletons.177df05e.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/index.4862150a.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/paths.517376d1.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/entry/app.09748b4b.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/index.6dd51b66.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/nodes/0.8897c14d.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/nodes/432.dbc9e824.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/Tip.de9bae2b.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/CodeBlock.864da1b0.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/EditOnGithub.7faefd25.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/HfOption.f7f04550.js">
 <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/stores.318eade7.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;AWQ&quot;,&quot;local&quot;:&quot;awq&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Fused modules&quot;,&quot;local&quot;:&quot;fused-modules&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ExLlamaV2&quot;,&quot;local&quot;:&quot;exllamav2&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;CPU&quot;,&quot;local&quot;:&quot;cpu&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Resources&quot;,&quot;local&quot;:&quot;resources&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="awq" 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="#awq"><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>AWQ</span></h1> <p data-svelte-h="svelte-1b3motd"><a href="https://hf.co/papers/2306.00978" rel="nofollow">Activation-aware Weight Quantization (AWQ)</a> preserves a small fraction of the weights that are important for LLM performance to compress a model to 4-bits with minimal performance degradation.</p> <p data-svelte-h="svelte-vomabp">There are several libraries for quantizing models with the AWQ algorithm, such as <a href="https://github.com/mit-han-lab/llm-awq" rel="nofollow">llm-awq</a>, <a href="https://github.com/casper-hansen/AutoAWQ" rel="nofollow">autoawq</a> or <a href="https://huggingface.co/docs/optimum/main/en/intel/optimization_inc" rel="nofollow">optimum-intel</a>. Transformers supports loading models quantized with the llm-awq and autoawq libraries. This guide will show you how to load models quantized with autoawq, but the process is similar for llm-awq quantized models.</p> <p data-svelte-h="svelte-14s6he6">Run the command below to install autoawq</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 -->pip install autoawq<!-- HTML_TAG_END --></pre></div> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-1kinopw">AutoAWQ downgrades Transformers to version 4.47.1. If you want to do inference with AutoAWQ, you may need to reinstall your Transformers’ version after installing AutoAWQ.</p></div> <p data-svelte-h="svelte-og22vq">Identify an AWQ-quantized model by checking the <code>quant_method</code> key in the models <a href="https://huggingface.co/TheBloke/zephyr-7B-alpha-AWQ/blob/main/config.json" rel="nofollow">config.json</a> file.</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-punctuation">{</span>
 <span class="hljs-attr">&quot;_name_or_path&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-string">&quot;/workspace/process/huggingfaceh4_zephyr-7b-alpha/source&quot;</span><span class="hljs-punctuation">,</span>
 <span class="hljs-attr">&quot;architectures&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span>
 <span class="hljs-string">&quot;MistralForCausalLM&quot;</span>
 <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span>
 ...
 ...
 ...
 <span class="hljs-attr">&quot;quantization_config&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span>
 <span class="hljs-attr">&quot;quant_method&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-string">&quot;awq&quot;</span><span class="hljs-punctuation">,</span>
 <span class="hljs-attr">&quot;zero_point&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-literal"><span class="hljs-keyword">true</span></span><span class="hljs-punctuation">,</span>
 <span class="hljs-attr">&quot;group_size&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-number">128</span><span class="hljs-punctuation">,</span>
 <span class="hljs-attr">&quot;bits&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-number">4</span><span class="hljs-punctuation">,</span>
 <span class="hljs-attr">&quot;version&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-string">&quot;gemm&quot;</span>
 <span class="hljs-punctuation">}</span>
<span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-f68dns">Load the AWQ-quantized model with <a href="/docs/transformers/pr_36839/en/main_classes/model#transformers.PreTrainedModel.from_pretrained">from_pretrained()</a>. This automatically sets the other weights to fp16 by default for performance reasons. Use the <code>torch_dtype</code> parameter to load these other weights in a different format.</p> <p data-svelte-h="svelte-1aa9pxo">If the model is loaded on the CPU, use the <code>device_map</code> parameter to move it to a 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 --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForCausalLM, AutoTokenizer
<span class="hljs-keyword">import</span> torch
model = AutoModelForCausalLM.from_pretrained(
 <span class="hljs-string">&quot;TheBloke/zephyr-7B-alpha-AWQ&quot;</span>,
 torch_dtype=torch.float32,
 device_map=<span class="hljs-string">&quot;cuda:0&quot;</span>
)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-42py21">Use <code>attn_implementation</code> to enable <a href="../perf_infer_gpu_one#flashattention-2">FlashAttention2</a> to further accelerate inference.</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> transformers <span class="hljs-keyword">import</span> AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
 <span class="hljs-string">&quot;TheBloke/zephyr-7B-alpha-AWQ&quot;</span>,
 attn_implementation=<span class="hljs-string">&quot;flash_attention_2&quot;</span>,
 device_map=<span class="hljs-string">&quot;cuda:0&quot;</span>
)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="fused-modules" 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="#fused-modules"><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>Fused modules</span></h2> <p data-svelte-h="svelte-32kkq6">Fused modules offer improved accuracy and performance. They are supported out-of-the-box for AWQ modules for <a href="https://huggingface.co/meta-llama" rel="nofollow">Llama</a> and <a href="https://huggingface.co/mistralai/Mistral-7B-v0.1" rel="nofollow">Mistral</a> architectures, but you can also fuse AWQ modules for unsupported architectures.</p> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-1b7phxi">Fused modules cannot be combined with other optimization techniques such as FlashAttention2.</p></div> <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">supported architectures </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">unsupported architectures </div></div> <div class="language-select"><p data-svelte-h="svelte-1khv3wn">Create an <a href="/docs/transformers/pr_36839/en/main_classes/quantization#transformers.AwqConfig">AwqConfig</a> and set the parameters <code>fuse_max_seq_len</code> and <code>do_fuse=True</code> to enable fused modules. The <code>fuse_max_seq_len</code> parameter is the total sequence length and it should include the context length and the expected generation length. Set it to a larger value to be safe.</p> <p data-svelte-h="svelte-1qsxkvh">The example below fuses the AWQ modules of the <a href="https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-AWQ" rel="nofollow">TheBloke/Mistral-7B-OpenOrca-AWQ</a> model.</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">import</span> torch
<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AwqConfig, AutoModelForCausalLM
quantization_config = AwqConfig(
 bits=<span class="hljs-number">4</span>,
 fuse_max_seq_len=<span class="hljs-number">512</span>,
 do_fuse=<span class="hljs-literal">True</span>,
)
model = AutoModelForCausalLM.from_pretrained(
 <span class="hljs-string">&quot;TheBloke/Mistral-7B-OpenOrca-AWQ&quot;</span>,
 quantization_config=quantization_config
).to(<span class="hljs-number">0</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-81zmsw">The <a href="https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-AWQ" rel="nofollow">TheBloke/Mistral-7B-OpenOrca-AWQ</a> model was benchmarked with <code>batch_size=1</code> with and without fused modules.</p> <figcaption class="text-center text-gray-500 text-lg" data-svelte-h="svelte-grefv0">Unfused module</figcaption> <table data-svelte-h="svelte-19aactm"><thead><tr><th align="right">Batch Size</th> <th align="right">Prefill Length</th> <th align="right">Decode Length</th> <th align="right">Prefill tokens/s</th> <th align="right">Decode tokens/s</th> <th align="left">Memory (VRAM)</th></tr></thead> <tbody><tr><td align="right">1</td> <td align="right">32</td> <td align="right">32</td> <td align="right">60.0984</td> <td align="right">38.4537</td> <td align="left">4.50 GB (5.68%)</td></tr> <tr><td align="right">1</td> <td align="right">64</td> <td align="right">64</td> <td align="right">1333.67</td> <td align="right">31.6604</td> <td align="left">4.50 GB (5.68%)</td></tr> <tr><td align="right">1</td> <td align="right">128</td> <td align="right">128</td> <td align="right">2434.06</td> <td align="right">31.6272</td> <td align="left">4.50 GB (5.68%)</td></tr> <tr><td align="right">1</td> <td align="right">256</td> <td align="right">256</td> <td align="right">3072.26</td> <td align="right">38.1731</td> <td align="left">4.50 GB (5.68%)</td></tr> <tr><td align="right">1</td> <td align="right">512</td> <td align="right">512</td> <td align="right">3184.74</td> <td align="right">31.6819</td> <td align="left">4.59 GB (5.80%)</td></tr> <tr><td align="right">1</td> <td align="right">1024</td> <td align="right">1024</td> <td align="right">3148.18</td> <td align="right">36.8031</td> <td align="left">4.81 GB (6.07%)</td></tr> <tr><td align="right">1</td> <td align="right">2048</td> <td align="right">2048</td> <td align="right">2927.33</td> <td align="right">35.2676</td> <td align="left">5.73 GB (7.23%)</td></tr></tbody></table> <figcaption class="text-center text-gray-500 text-lg" data-svelte-h="svelte-1r15bg7">Fused module</figcaption> <table data-svelte-h="svelte-19fczbk"><thead><tr><th align="right">Batch Size</th> <th align="right">Prefill Length</th> <th align="right">Decode Length</th> <th align="right">Prefill tokens/s</th> <th align="right">Decode tokens/s</th> <th align="left">Memory (VRAM)</th></tr></thead> <tbody><tr><td align="right">1</td> <td align="right">32</td> <td align="right">32</td> <td align="right">81.4899</td> <td align="right">80.2569</td> <td align="left">4.00 GB (5.05%)</td></tr> <tr><td align="right">1</td> <td align="right">64</td> <td align="right">64</td> <td align="right">1756.1</td> <td align="right">106.26</td> <td align="left">4.00 GB (5.05%)</td></tr> <tr><td align="right">1</td> <td align="right">128</td> <td align="right">128</td> <td align="right">2479.32</td> <td align="right">105.631</td> <td align="left">4.00 GB (5.06%)</td></tr> <tr><td align="right">1</td> <td align="right">256</td> <td align="right">256</td> <td align="right">1813.6</td> <td align="right">85.7485</td> <td align="left">4.01 GB (5.06%)</td></tr> <tr><td align="right">1</td> <td align="right">512</td> <td align="right">512</td> <td align="right">2848.9</td> <td align="right">97.701</td> <td align="left">4.11 GB (5.19%)</td></tr> <tr><td align="right">1</td> <td align="right">1024</td> <td align="right">1024</td> <td align="right">3044.35</td> <td align="right">87.7323</td> <td align="left">4.41 GB (5.57%)</td></tr> <tr><td align="right">1</td> <td align="right">2048</td> <td align="right">2048</td> <td align="right">2715.11</td> <td align="right">89.4709</td> <td align="left">5.57 GB (7.04%)</td></tr></tbody></table> <p data-svelte-h="svelte-gu8e8k">The speed and throughput of fused and unfused modules were also tested with the <a href="https://github.com/huggingface/optimum-benchmark" rel="nofollow">optimum-benchmark</a> library.</p> <div class="flex gap-4" data-svelte-h="svelte-1ke50ja"><div><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/quantization/fused_forward_memory_plot.png" alt="generate throughput per batch size"> <figcaption class="mt-2 text-center text-sm text-gray-500">forward peak memory/batch size</figcaption></div> <div><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/quantization/fused_generate_throughput_plot.png" alt="forward latency per batch size"> <figcaption class="mt-2 text-center text-sm text-gray-500">generate throughput/batch size</figcaption></div></div> </div> <h2 class="relative group"><a id="exllamav2" 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="#exllamav2"><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>ExLlamaV2</span></h2> <p data-svelte-h="svelte-1frcaex"><a href="https://github.com/turboderp/exllamav2" rel="nofollow">ExLlamaV2</a> kernels support faster prefill and decoding. Run the command below to install the latest version of autoawq with ExLlamaV2 support.</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 -->pip install git+https://github.com/casper-hansen/AutoAWQ.git<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-90wyji">Set <code>version=&quot;exllama&quot;</code> in <a href="/docs/transformers/pr_36839/en/main_classes/quantization#transformers.AwqConfig">AwqConfig</a> to enable ExLlamaV2 kernels.</p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1y6gcly">ExLlamaV2 is supported on AMD GPUs.</p></div> <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> transformers <span class="hljs-keyword">import</span> AutoModelForCausalLM, AutoTokenizer, AwqConfig
quantization_config = AwqConfig(version=<span class="hljs-string">&quot;exllama&quot;</span>)
model = AutoModelForCausalLM.from_pretrained(
 <span class="hljs-string">&quot;TheBloke/Mistral-7B-Instruct-v0.1-AWQ&quot;</span>,
 quantization_config=quantization_config,
 device_map=<span class="hljs-string">&quot;auto&quot;</span>,
)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="cpu" 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="#cpu"><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>CPU</span></h2> <p data-svelte-h="svelte-30l4yi"><a href="https://intel.github.io/intel-extension-for-pytorch/cpu/latest/" rel="nofollow">Intel Extension for PyTorch (IPEX)</a> is designed to enable performance optimizations on Intel hardware. Run the command below to install the latest version of autoawq with IPEX support.</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 -->pip install intel-extension-for-pytorch <span class="hljs-comment"># for IPEX-GPU refer to https://intel.github.io/intel-extension-for-pytorch/xpu/2.5.10+xpu/ </span>
pip install git+https://github.com/casper-hansen/AutoAWQ.git<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1i6md6o">Set <code>version=&quot;ipex&quot;</code> in <a href="/docs/transformers/pr_36839/en/main_classes/quantization#transformers.AwqConfig">AwqConfig</a> to enable ExLlamaV2 kernels.</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">import</span> torch
<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForCausalLM, AutoTokenizer, AwqConfig
device = <span class="hljs-string">&quot;cpu&quot;</span> <span class="hljs-comment"># set to &quot;xpu&quot; for Intel GPU</span>
quantization_config = AwqConfig(version=<span class="hljs-string">&quot;ipex&quot;</span>)
model = AutoModelForCausalLM.from_pretrained(
 <span class="hljs-string">&quot;TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ&quot;</span>,
 quantization_config=quantization_config,
 device_map=device,
)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="resources" 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="#resources"><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>Resources</span></h2> <p data-svelte-h="svelte-o4txta">Run the AWQ demo <a href="https://colab.research.google.com/drive/1HzZH89yAXJaZgwJDhQj9LqSBux932BvY#scrollTo=Wwsg6nCwoThm" rel="nofollow">notebook</a> for more examples of how to quantize a model, push a quantized model to the Hub, and more.</p> <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/en/quantization/awq.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_1bm5psi = {
 assets: "/docs/transformers/pr_36839/en",
 base: "/docs/transformers/pr_36839/en",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/transformers/pr_36839/en/_app/immutable/entry/start.6be8d590.js"),
 import("/docs/transformers/pr_36839/en/_app/immutable/entry/app.09748b4b.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 432],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
35.5 kB
·
Xet hash:
daf4498060e1b5b6f3918fa4808045f258f4da714caba3b3d4b82afe531a6aaf

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