[GH-PAGES] Updated website

master/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: d4e4dcd30405f5206b28830d08ce76de
+config: 255e5b7e27427f0ab6fda308ee6aef63
 tags: 645f666f9bcd5a90fca523b33c5a78b7

master/_sources/getting-started/tutorials/01-vector-add.rst.txt

@@ -235,10 +235,10 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     0        4096.0    9.600000    9.600000
     1        8192.0   19.200000   19.200000
     2       16384.0   38.400001   38.400001
-    3       32768.0   63.999998   76.800002
+    3       32768.0   76.800002   76.800002
     4       65536.0  127.999995  127.999995
     5      131072.0  219.428568  219.428568
-    6      262144.0  341.333321  341.333321
+    6      262144.0  341.333321  384.000001
     7      524288.0  472.615390  472.615390
     8     1048576.0  614.400016  614.400016
     9     2097152.0  722.823517  722.823517
@@ -255,7 +255,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  39.355 seconds)
+   **Total running time of the script:** ( 1 minutes  34.829 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt

@@ -284,11 +284,11 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
     3     640.0  706.206879      640.000002   160.000000
     4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
-    93  12160.0  812.359066      406.179533   198.733401
-    94  12288.0  812.429770      416.101597   198.995960
-    95  12416.0  812.498981      411.722274   198.655991
-    96  12544.0  810.925276      412.971190   198.913776
-    97  12672.0  811.007961      412.097543   199.069228
+    93  12160.0  812.359066      406.179533   198.936606
+    94  12288.0  812.429770      415.222812   199.298541
+    95  12416.0  812.498981      412.149375   198.954424
+    96  12544.0  812.566838      412.758863   199.209928
+    97  12672.0  811.007961      412.097543   199.264875
 
     [98 rows x 4 columns]
 
@@ -306,7 +306,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  22.426 seconds)
+   **Total running time of the script:** ( 3 minutes  18.076 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt

@@ -459,37 +459,37 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
 
     matmul-performance:
              M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
-    0    256.0   2.978909  ...   2.978909              3.276800
-    1    384.0   7.372800  ...   8.507077              8.507077
+    0    256.0   2.730667  ...   2.978909              2.978909
+    1    384.0   7.372800  ...   7.899428              7.899428
     2    512.0  14.563555  ...  15.420235             15.420235
     3    640.0  22.260869  ...  24.380953             24.380953
     4    768.0  32.768000  ...  35.389441             34.028308
-    5    896.0  39.025776  ...  40.140799             39.025776
+    5    896.0  37.971025  ...  40.140799             39.025776
     6   1024.0  49.932191  ...  53.773130             52.428801
     7   1152.0  45.242181  ...  48.161033             47.396572
     8   1280.0  51.200001  ...  57.690139             57.690139
-    9   1408.0  64.138541  ...  68.147202             66.485074
-    10  1536.0  80.430545  ...  81.355034             78.643199
-    11  1664.0  63.372618  ...  62.929456             62.492442
-    12  1792.0  72.983276  ...  72.983276             59.467852
-    13  1920.0  68.776119  ...  71.626943             71.257735
-    14  2048.0  73.584279  ...  78.398206             77.314362
-    15  2176.0  83.500614  ...  87.876193             85.998493
-    16  2304.0  68.643310  ...  78.064941             77.057651
+    9   1408.0  64.138541  ...  68.147202             65.684049
+    10  1536.0  79.526831  ...  81.355034             78.643199
+    11  1664.0  63.372618  ...  63.372618             62.492442
+    12  1792.0  72.983276  ...  72.983276             59.154861
+    13  1920.0  68.776119  ...  71.626943             70.892307
+    14  2048.0  73.584279  ...  78.033565             76.959706
+    15  2176.0  83.155572  ...  87.494120             86.367588
+    16  2304.0  68.446623  ...  78.064941             77.057651
     17  2432.0  71.305746  ...  86.179335             85.393507
-    18  2560.0  77.833728  ...  82.956960             81.512437
-    19  2688.0  84.108772  ...  91.185232             88.216412
-    20  2816.0  83.074685  ...  84.687779             83.074685
-    21  2944.0  82.102191  ...  83.617504             82.646820
-    22  3072.0  82.420822  ...  89.170242             88.335577
-    23  3200.0  84.432717  ...  97.338403             95.665176
-    24  3328.0  82.464255  ...  85.602017             83.516586
-    25  3456.0  81.849303  ...  92.033756             90.281712
-    26  3584.0  84.745889  ...  91.284657             95.960933
-    27  3712.0  85.822459  ...  88.483034             87.552452
-    28  3840.0  81.019778  ...  86.265212             89.620748
-    29  3968.0  86.911637  ...  92.512459             84.038524
-    30  4096.0  93.792965  ...  92.755862             87.552332
+    18  2560.0  77.833728  ...  82.956960             81.715711
+    19  2688.0  83.737433  ...  91.185232             89.464755
+    20  2816.0  82.446516  ...  84.523664             83.712490
+    21  2944.0  81.967162  ...  83.758038             82.373605
+    22  3072.0  82.420822  ...  88.750943             86.579673
+    23  3200.0  81.528664  ...  91.233074             95.665176
+    24  3328.0  83.516586  ...  85.908470             83.323259
+    25  3456.0  81.435930  ...  92.138932             90.180725
+    26  3584.0  83.954614  ...  91.189190             95.858629
+    27  3712.0  85.822459  ...  83.806497             87.783251
+    28  3840.0  80.901241  ...  89.259080             89.548180
+    29  3968.0  87.913500  ...  92.829164             84.096442
+    30  4096.0  93.825748  ...  89.299883             90.139506
 
     [31 rows x 5 columns]
 
@@ -499,7 +499,7 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 6 minutes  0.489 seconds)
+   **Total running time of the script:** ( 5 minutes  52.578 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

master/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt

@@ -240,7 +240,7 @@ References
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  0.467 seconds)
+   **Total running time of the script:** ( 0 minutes  0.476 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

master/_sources/getting-started/tutorials/05-layer-norm.rst.txt

@@ -41,27 +41,27 @@ Layer Normalization
     0    1024.0  585.142849  277.694907  468.114273
     1    1536.0  630.153868  323.368435  511.999982
     2    2048.0  682.666643  334.367358  520.126988
-    3    2560.0  694.237267  365.714281  512.000013
+    3    2560.0  694.237267  365.714281  518.481028
     4    3072.0  712.347810  378.092307  501.551037
-    5    3584.0  725.873439  384.859062  455.111115
+    5    3584.0  725.873439  384.859062  458.751978
     6    4096.0  728.177767  381.023256  458.293714
-    7    4608.0  676.403666  396.387087  431.157877
-    8    5120.0  688.403381  397.669909  422.268057
-    9    5632.0  704.000002  396.969169  417.185184
+    7    4608.0  670.254540  396.387087  426.173427
+    8    5120.0  694.237267  397.669909  426.666652
+    9    5632.0  704.000002  396.969169  413.357796
     10   6144.0  702.171410  402.885254  411.313806
-    11   6656.0  705.271522  400.360920  400.360920
-    12   7168.0  690.891575  396.844306  387.459443
+    11   6656.0  700.631610  400.360920  400.360920
+    12   7168.0  695.078767  396.844306  388.772874
     13   7680.0  682.666656  393.846167  387.634072
-    14   8192.0  636.271854  393.609605  371.308771
-    15   8704.0  630.153861  389.005597  380.502740
-    16   9216.0  609.322328  407.337026  383.999986
+    14   8192.0  642.509816  393.609605  372.363633
+    15   8704.0  627.315309  389.005597  380.502740
+    16   9216.0  606.814809  407.337026  383.999986
     17   9728.0  589.575753  409.599987  383.369452
     18  10240.0  566.920437  408.578556  382.803739
     19  10752.0  549.623009  411.559798  381.445676
     20  11264.0  536.380957  406.826188  373.134567
-    21  11776.0  523.377770  410.492372  378.345375
-    22  12288.0  516.031509  414.784810  383.251457
-    23  12800.0  505.679014  410.420828  377.163903
+    21  11776.0  523.377770  410.492372  377.587162
+    22  12288.0  517.389457  414.784810  383.251457
+    23  12800.0  505.679014  410.420828  376.470582
     24  13312.0  494.180982  405.699062  376.976995
     25  13824.0  482.934503  411.888257  379.389355
     26  14336.0  471.967074  406.695045  374.185964
@@ -389,7 +389,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  20.636 seconds)
+   **Total running time of the script:** ( 5 minutes  24.641 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

master/_sources/getting-started/tutorials/sg_execution_times.rst.txt

@@ -5,16 +5,16 @@
 
 Computation times
 =================
-**16:23.374** total execution time for **getting-started_tutorials** files:
+**16:10.599** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:00.489 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:52.578 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:20.636 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:24.641 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:22.426 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:18.076 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:39.355 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:34.829 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.467 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.476 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

master/getting-started/tutorials/01-vector-add.html

@@ -325,10 +325,10 @@ for different problem sizes.</p>
 0        4096.0    9.600000    9.600000
 1        8192.0   19.200000   19.200000
 2       16384.0   38.400001   38.400001
-3       32768.0   63.999998   76.800002
+3       32768.0   76.800002   76.800002
 4       65536.0  127.999995  127.999995
 5      131072.0  219.428568  219.428568
-6      262144.0  341.333321  341.333321
+6      262144.0  341.333321  384.000001
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
 9     2097152.0  722.823517  722.823517
@@ -340,7 +340,7 @@ for different problem sizes.</p>
 15  134217728.0  849.737435  850.656574
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  39.355 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  34.829 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-01-vector-add-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/62d97d49a32414049819dd8bb8378080/01-vector-add.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">01-vector-add.py</span></code></a></p>

master/getting-started/tutorials/02-fused-softmax.html

@@ -375,11 +375,11 @@ We will then compare its performance against (1) <code class="code docutils lite
 3     640.0  706.206879      640.000002   160.000000
 4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
-93  12160.0  812.359066      406.179533   198.733401
-94  12288.0  812.429770      416.101597   198.995960
-95  12416.0  812.498981      411.722274   198.655991
-96  12544.0  810.925276      412.971190   198.913776
-97  12672.0  811.007961      412.097543   199.069228
+93  12160.0  812.359066      406.179533   198.936606
+94  12288.0  812.429770      415.222812   199.298541
+95  12416.0  812.498981      412.149375   198.954424
+96  12544.0  812.566838      412.758863   199.209928
+97  12672.0  811.007961      412.097543   199.264875
 
 [98 rows x 4 columns]
 </pre></div>
@@ -392,7 +392,7 @@ We will then compare its performance against (1) <code class="code docutils lite
 Note however that the PyTorch <cite>softmax</cite> operation is more general and will works on tensors of any shape.</p></li>
 </ul>
 </div></blockquote>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  22.426 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  18.076 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-02-fused-softmax-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/d91442ac2982c4e0cc3ab0f43534afbc/02-fused-softmax.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">02-fused-softmax.py</span></code></a></p>

master/getting-started/tutorials/03-matrix-multiplication.html

@@ -565,42 +565,42 @@ torch_output=tensor([[  1.1045, -36.9688,  31.4688,  ..., -11.3906,  24.4531, -3
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>matmul-performance:
          M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
-0    256.0   2.978909  ...   2.978909              3.276800
-1    384.0   7.372800  ...   8.507077              8.507077
+0    256.0   2.730667  ...   2.978909              2.978909
+1    384.0   7.372800  ...   7.899428              7.899428
 2    512.0  14.563555  ...  15.420235             15.420235
 3    640.0  22.260869  ...  24.380953             24.380953
 4    768.0  32.768000  ...  35.389441             34.028308
-5    896.0  39.025776  ...  40.140799             39.025776
+5    896.0  37.971025  ...  40.140799             39.025776
 6   1024.0  49.932191  ...  53.773130             52.428801
 7   1152.0  45.242181  ...  48.161033             47.396572
 8   1280.0  51.200001  ...  57.690139             57.690139
-9   1408.0  64.138541  ...  68.147202             66.485074
-10  1536.0  80.430545  ...  81.355034             78.643199
-11  1664.0  63.372618  ...  62.929456             62.492442
-12  1792.0  72.983276  ...  72.983276             59.467852
-13  1920.0  68.776119  ...  71.626943             71.257735
-14  2048.0  73.584279  ...  78.398206             77.314362
-15  2176.0  83.500614  ...  87.876193             85.998493
-16  2304.0  68.643310  ...  78.064941             77.057651
+9   1408.0  64.138541  ...  68.147202             65.684049
+10  1536.0  79.526831  ...  81.355034             78.643199
+11  1664.0  63.372618  ...  63.372618             62.492442
+12  1792.0  72.983276  ...  72.983276             59.154861
+13  1920.0  68.776119  ...  71.626943             70.892307
+14  2048.0  73.584279  ...  78.033565             76.959706
+15  2176.0  83.155572  ...  87.494120             86.367588
+16  2304.0  68.446623  ...  78.064941             77.057651
 17  2432.0  71.305746  ...  86.179335             85.393507
-18  2560.0  77.833728  ...  82.956960             81.512437
-19  2688.0  84.108772  ...  91.185232             88.216412
-20  2816.0  83.074685  ...  84.687779             83.074685
-21  2944.0  82.102191  ...  83.617504             82.646820
-22  3072.0  82.420822  ...  89.170242             88.335577
-23  3200.0  84.432717  ...  97.338403             95.665176
-24  3328.0  82.464255  ...  85.602017             83.516586
-25  3456.0  81.849303  ...  92.033756             90.281712
-26  3584.0  84.745889  ...  91.284657             95.960933
-27  3712.0  85.822459  ...  88.483034             87.552452
-28  3840.0  81.019778  ...  86.265212             89.620748
-29  3968.0  86.911637  ...  92.512459             84.038524
-30  4096.0  93.792965  ...  92.755862             87.552332
+18  2560.0  77.833728  ...  82.956960             81.715711
+19  2688.0  83.737433  ...  91.185232             89.464755
+20  2816.0  82.446516  ...  84.523664             83.712490
+21  2944.0  81.967162  ...  83.758038             82.373605
+22  3072.0  82.420822  ...  88.750943             86.579673
+23  3200.0  81.528664  ...  91.233074             95.665176
+24  3328.0  83.516586  ...  85.908470             83.323259
+25  3456.0  81.435930  ...  92.138932             90.180725
+26  3584.0  83.954614  ...  91.189190             95.858629
+27  3712.0  85.822459  ...  83.806497             87.783251
+28  3840.0  80.901241  ...  89.259080             89.548180
+29  3968.0  87.913500  ...  92.829164             84.096442
+30  4096.0  93.825748  ...  89.299883             90.139506
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  0.489 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  52.578 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-03-matrix-multiplication-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/d5fee5b55a64e47f1b5724ec39adf171/03-matrix-multiplication.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">03-matrix-multiplication.py</span></code></a></p>

master/getting-started/tutorials/04-low-memory-dropout.html

@@ -372,7 +372,7 @@ to explore the <cite>triton/language/random</cite> folder!</p>
 <dd><p>Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting”, JMLR 2014</p>
 </dd>
 </dl>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.467 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.476 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-04-low-memory-dropout-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/c9aed78977a4c05741d675a38dde3d7d/04-low-memory-dropout.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">04-low-memory-dropout.py</span></code></a></p>

master/getting-started/tutorials/05-layer-norm.html

@@ -197,27 +197,27 @@ to download the full example code</p>
 0    1024.0  585.142849  277.694907  468.114273
 1    1536.0  630.153868  323.368435  511.999982
 2    2048.0  682.666643  334.367358  520.126988
-3    2560.0  694.237267  365.714281  512.000013
+3    2560.0  694.237267  365.714281  518.481028
 4    3072.0  712.347810  378.092307  501.551037
-5    3584.0  725.873439  384.859062  455.111115
+5    3584.0  725.873439  384.859062  458.751978
 6    4096.0  728.177767  381.023256  458.293714
-7    4608.0  676.403666  396.387087  431.157877
-8    5120.0  688.403381  397.669909  422.268057
-9    5632.0  704.000002  396.969169  417.185184
+7    4608.0  670.254540  396.387087  426.173427
+8    5120.0  694.237267  397.669909  426.666652
+9    5632.0  704.000002  396.969169  413.357796
 10   6144.0  702.171410  402.885254  411.313806
-11   6656.0  705.271522  400.360920  400.360920
-12   7168.0  690.891575  396.844306  387.459443
+11   6656.0  700.631610  400.360920  400.360920
+12   7168.0  695.078767  396.844306  388.772874
 13   7680.0  682.666656  393.846167  387.634072
-14   8192.0  636.271854  393.609605  371.308771
-15   8704.0  630.153861  389.005597  380.502740
-16   9216.0  609.322328  407.337026  383.999986
+14   8192.0  642.509816  393.609605  372.363633
+15   8704.0  627.315309  389.005597  380.502740
+16   9216.0  606.814809  407.337026  383.999986
 17   9728.0  589.575753  409.599987  383.369452
 18  10240.0  566.920437  408.578556  382.803739
 19  10752.0  549.623009  411.559798  381.445676
 20  11264.0  536.380957  406.826188  373.134567
-21  11776.0  523.377770  410.492372  378.345375
-22  12288.0  516.031509  414.784810  383.251457
-23  12800.0  505.679014  410.420828  377.163903
+21  11776.0  523.377770  410.492372  377.587162
+22  12288.0  517.389457  414.784810  383.251457
+23  12800.0  505.679014  410.420828  376.470582
 24  13312.0  494.180982  405.699062  376.976995
 25  13824.0  482.934503  411.888257  379.389355
 26  14336.0  471.967074  406.695045  374.185964
@@ -537,7 +537,7 @@ to download the full example code</p>
 <span class="n">bench_layer_norm</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">save_path</span><span class="o">=</span><span class="s1">&#39;.&#39;</span><span class="p">,</span> <span class="n">print_data</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  20.636 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  24.641 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-05-layer-norm-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/935c0dd0fbeb4b2e69588471cbb2d4b2/05-layer-norm.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">05-layer-norm.py</span></code></a></p>

master/getting-started/tutorials/sg_execution_times.html

@@ -174,7 +174,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-getting-started-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>16:23.374</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>16:10.599</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -183,23 +183,23 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="03-matrix-multiplication.html#sphx-glr-getting-started-tutorials-03-matrix-multiplication-py"><span class="std std-ref">Matrix Multiplication</span></a> (<code class="docutils literal notranslate"><span class="pre">03-matrix-multiplication.py</span></code>)</p></td>
-<td><p>06:00.489</p></td>
+<td><p>05:52.578</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="05-layer-norm.html#sphx-glr-getting-started-tutorials-05-layer-norm-py"><span class="std std-ref">Layer Normalization</span></a> (<code class="docutils literal notranslate"><span class="pre">05-layer-norm.py</span></code>)</p></td>
-<td><p>05:20.636</p></td>
+<td><p>05:24.641</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="02-fused-softmax.html#sphx-glr-getting-started-tutorials-02-fused-softmax-py"><span class="std std-ref">Fused Softmax</span></a> (<code class="docutils literal notranslate"><span class="pre">02-fused-softmax.py</span></code>)</p></td>
-<td><p>03:22.426</p></td>
+<td><p>03:18.076</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="01-vector-add.html#sphx-glr-getting-started-tutorials-01-vector-add-py"><span class="std std-ref">Vector Addition</span></a> (<code class="docutils literal notranslate"><span class="pre">01-vector-add.py</span></code>)</p></td>
-<td><p>01:39.355</p></td>
+<td><p>01:34.829</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="04-low-memory-dropout.html#sphx-glr-getting-started-tutorials-04-low-memory-dropout-py"><span class="std std-ref">Low-Memory Dropout</span></a> (<code class="docutils literal notranslate"><span class="pre">04-low-memory-dropout.py</span></code>)</p></td>
-<td><p>00:00.467</p></td>
+<td><p>00:00.476</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>

v1.1.2/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 37ba5f351b70fa5546a6b2ed0bf86515
+config: e38b42b0e79f6250810f1562672b009a
 tags: 645f666f9bcd5a90fca523b33c5a78b7