mirror of
https://github.com/ml-explore/mlx.git
synced 2025-09-19 02:38:09 +08:00
rebase
This commit is contained in:
Awni Hannun
committed by
CircleCI Docs
CircleCI Docs
parent
a68317ae17
commit
a35796f0ea
@@ -8,7 +8,7 @@
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
|
||||
|
||||
<title>mlx.nn.quantize — MLX 0.18.0 documentation</title>
|
||||
<title>mlx.nn.quantize — MLX 0.18.1 documentation</title>
|
||||
|
||||
|
||||
|
||||
@@ -36,7 +36,7 @@
|
||||
<link rel="preload" as="script" href="../../_static/scripts/pydata-sphinx-theme.js?digest=5b4479735964841361fd" />
|
||||
<script src="../../_static/vendor/fontawesome/6.1.2/js/all.min.js?digest=5b4479735964841361fd"></script>
|
||||
|
||||
<script src="../../_static/documentation_options.js?v=4033e70d"></script>
|
||||
<script src="../../_static/documentation_options.js?v=fbcf6510"></script>
|
||||
<script src="../../_static/doctools.js?v=888ff710"></script>
|
||||
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script src="../../_static/scripts/sphinx-book-theme.js?v=efea14e4"></script>
|
||||
@@ -131,8 +131,8 @@
|
||||
|
||||
|
||||
|
||||
<img src="../../_static/mlx_logo.png" class="logo__image only-light" alt="MLX 0.18.0 documentation - Home"/>
|
||||
<script>document.write(`<img src="../../_static/mlx_logo_dark.png" class="logo__image only-dark" alt="MLX 0.18.0 documentation - Home"/>`);</script>
|
||||
<img src="../../_static/mlx_logo.png" class="logo__image only-light" alt="MLX 0.18.1 documentation - Home"/>
|
||||
<script>document.write(`<img src="../../_static/mlx_logo_dark.png" class="logo__image only-dark" alt="MLX 0.18.1 documentation - Home"/>`);</script>
|
||||
|
||||
|
||||
</a></div>
|
||||
@@ -370,6 +370,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.repeat.html">mlx.core.repeat</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.reshape.html">mlx.core.reshape</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.right_shift.html">mlx.core.right_shift</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.roll.html">mlx.core.roll</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.round.html">mlx.core.round</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.rsqrt.html">mlx.core.rsqrt</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.save.html">mlx.core.save</a></li>
|
||||
@@ -425,6 +426,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.random.truncated_normal.html">mlx.core.random.truncated_normal</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.random.uniform.html">mlx.core.random.uniform</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.random.laplace.html">mlx.core.random.laplace</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="mlx.core.random.permutation.html">mlx.core.random.permutation</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1 has-children"><a class="reference internal" href="../transforms.html">Transforms</a><input class="toctree-checkbox" id="toctree-checkbox-6" name="toctree-checkbox-6" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-6"><i class="fa-solid fa-chevron-down"></i></label><ul>
|
||||
@@ -871,7 +873,7 @@ document.write(`
|
||||
<h1>mlx.nn.quantize<a class="headerlink" href="#mlx-nn-quantize" title="Link to this heading">#</a></h1>
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="mlx.nn.quantize">
|
||||
<span class="sig-name descname"><span class="pre">quantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../nn/module.html#mlx.nn.Module" title="mlx.nn.layers.base.Module"><span class="pre">Module</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_size</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">64</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bits</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">class_predicate</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.12)"><span class="pre">Callable</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#mlx.nn.quantize" title="Link to this definition">#</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">quantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../nn/module.html#mlx.nn.Module" title="mlx.nn.layers.base.Module"><span class="pre">Module</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_size</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">64</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bits</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">class_predicate</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.13)"><span class="pre">Callable</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#mlx.nn.quantize" title="Link to this definition">#</a></dt>
|
||||
<dd><p>Quantize the sub-modules of a module according to a predicate.</p>
|
||||
<p>By default all layers that define a <code class="docutils literal notranslate"><span class="pre">to_quantized(group_size,</span> <span class="pre">bits)</span></code>
|
||||
method will be quantized. Both <a class="reference internal" href="../nn/_autosummary/mlx.nn.Linear.html#mlx.nn.Linear" title="mlx.nn.Linear"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Linear</span></code></a> and <a class="reference internal" href="../nn/_autosummary/mlx.nn.Embedding.html#mlx.nn.Embedding" title="mlx.nn.Embedding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Embedding</span></code></a> layers
|
||||
@@ -880,9 +882,9 @@ will be quantized. Note also, the module is updated in-place.</p>
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>model</strong> (<a class="reference internal" href="../nn/module.html#mlx.nn.Module" title="mlx.nn.Module"><em>Module</em></a>) – The model whose leaf modules may be quantized.</p></li>
|
||||
<li><p><strong>group_size</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – The quantization group size (see
|
||||
<li><p><strong>group_size</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a>) – The quantization group size (see
|
||||
<a class="reference internal" href="mlx.core.quantize.html#mlx.core.quantize" title="mlx.core.quantize"><code class="xref py py-func docutils literal notranslate"><span class="pre">mlx.core.quantize()</span></code></a>). Default: <code class="docutils literal notranslate"><span class="pre">64</span></code>.</p></li>
|
||||
<li><p><strong>bits</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – The number of bits per parameter (see
|
||||
<li><p><strong>bits</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a>) – The number of bits per parameter (see
|
||||
<a class="reference internal" href="mlx.core.quantize.html#mlx.core.quantize" title="mlx.core.quantize"><code class="xref py py-func docutils literal notranslate"><span class="pre">mlx.core.quantize()</span></code></a>). Default: <code class="docutils literal notranslate"><span class="pre">4</span></code>.</p></li>
|
||||
<li><p><strong>class_predicate</strong> (<em>Optional</em><em>[</em><em>Callable</em><em>]</em>) – A callable which receives the
|
||||
<a class="reference internal" href="../nn/module.html#mlx.nn.Module" title="mlx.nn.Module"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Module</span></code></a> path and <a class="reference internal" href="../nn/module.html#mlx.nn.Module" title="mlx.nn.Module"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Module</span></code></a> itself and returns <code class="docutils literal notranslate"><span class="pre">True</span></code> if
|
||||
|
||||
Reference in New Issue
Block a user