rebase

docs/build/html/python/ops.html

@@ -8,7 +8,7 @@
     <meta charset="utf-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
 
-    <title>Operations &#8212; MLX 0.28.0 documentation</title>
+    <title>Operations &#8212; MLX 0.29.0 documentation</title>
   
   
   
@@ -30,15 +30,18 @@
 
     <link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=03e43079" />
     <link rel="stylesheet" type="text/css" href="../_static/styles/sphinx-book-theme.css?v=eba8b062" />
+    <link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
   
   <!-- Pre-loaded scripts that we'll load fully later -->
   <link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
 <link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
   <script src="../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
 
-    <script src="../_static/documentation_options.js?v=60827de6"></script>
+    <script src="../_static/documentation_options.js?v=9c58480a"></script>
     <script src="../_static/doctools.js?v=9a2dae69"></script>
     <script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
+    <script src="../_static/clipboard.min.js?v=a7894cd8"></script>
+    <script src="../_static/copybutton.js?v=f281be69"></script>
     <script src="../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
     <script async="async" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
     <script>DOCUMENTATION_OPTIONS.pagename = 'python/ops';</script>
@@ -138,8 +141,8 @@
       
     
     
-    <img src="../_static/mlx_logo.png" class="logo__image only-light" alt="MLX 0.28.0 documentation - Home"/>
-    <script>document.write(`<img src="../_static/mlx_logo_dark.png" class="logo__image only-dark" alt="MLX 0.28.0 documentation - Home"/>`);</script>
+    <img src="../_static/mlx_logo.png" class="logo__image only-light" alt="MLX 0.29.0 documentation - Home"/>
+    <script>document.write(`<img src="../_static/mlx_logo_dark.png" class="logo__image only-dark" alt="MLX 0.29.0 documentation - Home"/>`);</script>
   
   
 </a></div>
@@ -478,6 +481,7 @@
 <li class="toctree-l2"><a class="reference internal" href="_autosummary/mlx.core.fast.rope.html">mlx.core.fast.rope</a></li>
 <li class="toctree-l2"><a class="reference internal" href="_autosummary/mlx.core.fast.scaled_dot_product_attention.html">mlx.core.fast.scaled_dot_product_attention</a></li>
 <li class="toctree-l2"><a class="reference internal" href="_autosummary/mlx.core.fast.metal_kernel.html">mlx.core.fast.metal_kernel</a></li>
+<li class="toctree-l2"><a class="reference internal" href="_autosummary/mlx.core.fast.cuda_kernel.html">mlx.core.fast.cuda_kernel</a></li>
 </ul>
 </details></li>
 <li class="toctree-l1 has-children"><a class="reference internal" href="fft.html">FFT</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
@@ -524,6 +528,10 @@
 <li class="toctree-l2"><a class="reference internal" href="_autosummary/mlx.core.metal.stop_capture.html">mlx.core.metal.stop_capture</a></li>
 </ul>
 </details></li>
+<li class="toctree-l1 has-children"><a class="reference internal" href="cuda.html">CUDA</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
+<li class="toctree-l2"><a class="reference internal" href="_autosummary/mlx.core.cuda.is_available.html">mlx.core.cuda.is_available</a></li>
+</ul>
+</details></li>
 <li class="toctree-l1 has-children"><a class="reference internal" href="memory_management.html">Memory Management</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
 <li class="toctree-l2"><a class="reference internal" href="_autosummary/mlx.core.get_active_memory.html">mlx.core.get_active_memory</a></li>
 <li class="toctree-l2"><a class="reference internal" href="_autosummary/mlx.core.get_peak_memory.html">mlx.core.get_peak_memory</a></li>
@@ -1066,8 +1074,8 @@ document.write(`
 <tr class="row-odd"><td><p><a class="reference internal" href="_autosummary/mlx.core.degrees.html#mlx.core.degrees" title="mlx.core.degrees"><code class="xref py py-obj docutils literal notranslate"><span class="pre">degrees</span></code></a>(a, /, *[, stream])</p></td>
 <td><p>Convert angles from radians to degrees.</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="_autosummary/mlx.core.dequantize.html#mlx.core.dequantize" title="mlx.core.dequantize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">dequantize</span></code></a>(w, /, scales, biases[, ...])</p></td>
-<td><p>Dequantize the matrix <code class="docutils literal notranslate"><span class="pre">w</span></code> using the provided <code class="docutils literal notranslate"><span class="pre">scales</span></code> and <code class="docutils literal notranslate"><span class="pre">biases</span></code> and the <code class="docutils literal notranslate"><span class="pre">group_size</span></code> and <code class="docutils literal notranslate"><span class="pre">bits</span></code> configuration.</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="_autosummary/mlx.core.dequantize.html#mlx.core.dequantize" title="mlx.core.dequantize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">dequantize</span></code></a>(w, /, scales, biases, group_size, ...)</p></td>
+<td><p>Dequantize the matrix <code class="docutils literal notranslate"><span class="pre">w</span></code> using quantization parameters.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="_autosummary/mlx.core.diag.html#mlx.core.diag" title="mlx.core.diag"><code class="xref py py-obj docutils literal notranslate"><span class="pre">diag</span></code></a>(a, /[, k, stream])</p></td>
 <td><p>Extract a diagonal or construct a diagonal matrix.</p></td>
@@ -1123,7 +1131,7 @@ document.write(`
 <tr class="row-even"><td><p><a class="reference internal" href="_autosummary/mlx.core.gather_mm.html#mlx.core.gather_mm" title="mlx.core.gather_mm"><code class="xref py py-obj docutils literal notranslate"><span class="pre">gather_mm</span></code></a>(a, b, /, lhs_indices, rhs_indices, *)</p></td>
 <td><p>Matrix multiplication with matrix-level gather.</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="_autosummary/mlx.core.gather_qmm.html#mlx.core.gather_qmm" title="mlx.core.gather_qmm"><code class="xref py py-obj docutils literal notranslate"><span class="pre">gather_qmm</span></code></a>(x, w, /, scales, biases[, ...])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="_autosummary/mlx.core.gather_qmm.html#mlx.core.gather_qmm" title="mlx.core.gather_qmm"><code class="xref py py-obj docutils literal notranslate"><span class="pre">gather_qmm</span></code></a>(x, w, /, scales[, biases, ...])</p></td>
 <td><p>Perform quantized matrix multiplication with matrix-level gather.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="_autosummary/mlx.core.greater.html#mlx.core.greater" title="mlx.core.greater"><code class="xref py py-obj docutils literal notranslate"><span class="pre">greater</span></code></a>(a, b[, stream])</p></td>
@@ -1273,10 +1281,10 @@ document.write(`
 <tr class="row-even"><td><p><a class="reference internal" href="_autosummary/mlx.core.put_along_axis.html#mlx.core.put_along_axis" title="mlx.core.put_along_axis"><code class="xref py py-obj docutils literal notranslate"><span class="pre">put_along_axis</span></code></a>(a, /, indices, values[, ...])</p></td>
 <td><p>Put values along an axis at the specified indices.</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="_autosummary/mlx.core.quantize.html#mlx.core.quantize" title="mlx.core.quantize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">quantize</span></code></a>(w, /[, group_size, bits, stream])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="_autosummary/mlx.core.quantize.html#mlx.core.quantize" title="mlx.core.quantize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">quantize</span></code></a>(w, /[, group_size, bits, mode, stream])</p></td>
 <td><p>Quantize the matrix <code class="docutils literal notranslate"><span class="pre">w</span></code> using <code class="docutils literal notranslate"><span class="pre">bits</span></code> bits per element.</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="_autosummary/mlx.core.quantized_matmul.html#mlx.core.quantized_matmul" title="mlx.core.quantized_matmul"><code class="xref py py-obj docutils literal notranslate"><span class="pre">quantized_matmul</span></code></a>(x, w, /, scales, biases[, ...])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="_autosummary/mlx.core.quantized_matmul.html#mlx.core.quantized_matmul" title="mlx.core.quantized_matmul"><code class="xref py py-obj docutils literal notranslate"><span class="pre">quantized_matmul</span></code></a>(x, w, /, scales[, biases, ...])</p></td>
 <td><p>Perform the matrix multiplication with the quantized matrix <code class="docutils literal notranslate"><span class="pre">w</span></code>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="_autosummary/mlx.core.radians.html#mlx.core.radians" title="mlx.core.radians"><code class="xref py py-obj docutils literal notranslate"><span class="pre">radians</span></code></a>(a, /, *[, stream])</p></td>