[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: 6652bf2efe5c4422cc1b6d7b8757f15f
+config: c8a6bdf06c7d292a5b258b2deb3c528d
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -235,17 +235,17 @@ 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   76.800002   76.800002
+    3       32768.0   63.999998   76.800002
     4       65536.0  127.999995  127.999995
     5      131072.0  219.428568  219.428568
-    6      262144.0  384.000001  384.000001
+    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
     10    4194304.0  780.190482  780.190482
     11    8388608.0  812.429770  812.429770
     12   16777216.0  833.084721  833.084721
-    13   33554432.0  842.004273  843.811163
+    13   33554432.0  842.004273  842.004273
     14   67108864.0  847.448255  848.362445
     15  134217728.0  849.737435  850.656574
 
@@ -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  40.829 seconds)
+   **Total running time of the script:** ( 1 minutes  45.824 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

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

@@ -278,17 +278,17 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
 
     softmax-performance:
               N      Triton  Torch (native)  Torch (jit)
-    0     256.0  512.000001      546.133347   186.181817
+    0     256.0  512.000001      546.133347   188.321838
-    1     384.0  614.400016      585.142862   153.600004
+    1     384.0  585.142862      558.545450   153.600004
-    2     512.0  655.360017      606.814814   156.038096
+    2     512.0  655.360017      606.814814   154.566038
     3     640.0  706.206879      640.000002   160.000000
     4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
-    93  12160.0  814.058574      406.179533   199.140227
+    93  12160.0  814.058574      405.333344   198.834951
-    94  12288.0  814.111783      415.222812   199.399583
+    94  12288.0  814.111783      415.222812   199.096718
-    95  12416.0  814.163950      412.149375   198.954424
+    95  12416.0  814.163950      411.296057   198.755369
-    96  12544.0  814.214963      412.971190   199.209928
+    96  12544.0  814.214963      412.546756   198.913776
-    97  12672.0  814.265046      412.097543   199.264875
+    97  12672.0  814.265046      412.097543   199.069228
 
     [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  21.705 seconds)
+   **Total running time of the script:** ( 3 minutes  21.745 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -458,37 +458,37 @@ 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  ...   3.276800              2.978909
+    0    256.0   2.730667  ...   2.978909              2.978909
-    1    384.0   7.372800  ...   8.507077              8.507077
+    1    384.0   7.372800  ...   7.899428              8.507077
-    2    512.0  14.563555  ...  16.384000             16.384000
+    2    512.0  14.563555  ...  16.384000             15.420235
-    3    640.0  23.272727  ...  24.380953             24.380953
+    3    640.0  22.260869  ...  24.380953             24.380953
     4    768.0  32.768000  ...  34.028308             34.028308
-    5    896.0  39.025776  ...  40.140799             39.025776
+    5    896.0  39.025776  ...  40.140799             37.971025
-    6   1024.0  51.150050  ...  52.428801             52.428801
+    6   1024.0  49.932191  ...  52.428801             52.428801
     7   1152.0  45.242181  ...  46.656000             46.656000
     8   1280.0  51.200001  ...  56.888887             56.888887
     9   1408.0  64.138541  ...  67.305878             66.485074
     10  1536.0  80.430545  ...  79.526831             78.643199
-    11  1664.0  62.929456  ...  62.492442             62.061463
+    11  1664.0  62.929456  ...  62.061463             62.492442
-    12  1792.0  72.512412  ...  72.047592             71.588687
+    12  1792.0  72.512412  ...  71.588687             72.047592
-    13  1920.0  68.776119  ...  70.530615             69.818184
+    13  1920.0  69.467336  ...  70.172588             70.172588
-    14  2048.0  73.584279  ...  76.608294             76.608294
+    14  2048.0  73.262953  ...  76.608294             76.260072
-    15  2176.0  83.500614  ...  85.998493             85.632545
+    15  2176.0  83.155572  ...  85.998493             85.998493
-    16  2304.0  68.643310  ...  76.809875             76.563695
+    16  2304.0  68.643310  ...  76.809875             76.809875
-    17  2432.0  71.487187  ...  83.119713             85.134737
+    17  2432.0  71.487187  ...  74.521127             84.877538
-    18  2560.0  78.019048  ...  80.511054             80.511054
+    18  2560.0  77.833728  ...  81.108913             80.808877
-    19  2688.0  83.737433  ...  89.888756             89.464755
+    19  2688.0  82.823267  ...  89.676257             89.464755
-    20  2816.0  82.602666  ...  82.759409             82.602666
+    20  2816.0  80.617762  ...  82.602666             83.392363
-    21  2944.0  82.102191  ...  82.509987             82.784108
+    21  2944.0  81.832567  ...  82.102191             82.102191
-    22  3072.0  82.661468  ...  87.924073             85.275760
+    22  3072.0  82.121977  ...  88.335577             86.911900
-    23  3200.0  84.993363  ...  95.665176             94.674553
+    23  3200.0  78.717759  ...  91.559367             92.753621
-    24  3328.0  82.939284  ...  83.130825             84.596116
+    24  3328.0  79.990330  ...  83.130825             83.905938
-    25  3456.0  81.766291  ...  91.097818             84.597660
+    25  3456.0  81.724858  ...  91.304157             90.892410
-    26  3584.0  84.905939  ...  93.759530             87.296493
+    26  3584.0  83.101104  ...  91.563533             96.579370
-    27  3712.0  84.159518  ...  86.341700             86.867254
+    27  3712.0  85.748791  ...  86.045381             91.901879
-    28  3840.0  84.874902  ...  92.236860             84.552479
+    28  3840.0  80.313725  ...  86.265212             91.322872
-    29  3968.0  92.302520  ...  84.098250             90.791620
+    29  3968.0  86.911637  ...  90.221021             83.922926
-    30  4096.0  86.426548  ...  85.434583             91.180520
+    30  4096.0  92.755862  ...  88.301134             82.342167
 
     [31 rows x 5 columns]
 
@@ -498,7 +498,7 @@ 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  6.796 seconds)
+   **Total running time of the script:** ( 6 minutes  5.749 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  0.496 seconds)
+   **Total running time of the script:** ( 0 minutes  0.493 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

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

@@ -38,36 +38,36 @@ Layer Normalization
 
     layer-norm-backward:
               N      Triton       Torch        Apex
-    0    1024.0  311.088617   98.303995  307.200008
+    0    1024.0  307.200008   95.255819  292.571431
-    1    1536.0  347.773587  134.540150  344.523365
+    1    1536.0  347.773587  135.529409  344.523365
-    2    2048.0  423.724127  161.684218  325.509933
+    2    2048.0  420.102553  162.217818  325.509933
-    3    2560.0  458.507457  181.775141  326.808501
+    3    2560.0  451.764698  183.402991  330.322572
-    4    3072.0  511.999982  192.501302  319.168834
+    4    3072.0  515.580429  191.501303  317.793096
-    5    3584.0  551.384634  208.271186  311.652167
+    5    3584.0  547.872604  207.768111  311.652167
-    6    4096.0  568.231237  220.412561  299.707322
+    6    4096.0  564.965515  220.907859  301.546004
-    7    4608.0  507.302750  232.825259  286.507772
+    7    4608.0  504.986315  232.825259  288.751954
-    8    5120.0  529.655159  242.845844  284.444444
+    8    5120.0  531.948056  242.845844  285.104413
-    9    5632.0  545.032265  243.545956  290.060087
+    9    5632.0  545.032265  243.107920  290.060087
-    10   6144.0  548.163546  248.661056  286.879370
+    10   6144.0  548.163546  250.349744  286.879370
-    11   6656.0  534.260858  256.000009  285.767438
+    11   6656.0  537.858601  254.775119  285.767438
-    12   7168.0  507.469040  260.654538  286.242939
+    12   7168.0  508.970395  256.000002  279.726817
-    13   7680.0  481.253256  262.564106  279.272719
+    13   7680.0  485.052616  263.690977  278.009056
-    14   8192.0  462.607053  267.130429  284.939124
+    14   8192.0  462.607053  264.258058  280.068380
-    15   8704.0  417.791980  267.815384  285.377055
+    15   8704.0  417.791980  263.757583  282.291896
-    16   9216.0  431.157889  272.394084  288.751954
+    16   9216.0  430.319054  270.727053  286.879380
-    17   9728.0  439.683593  280.615388  290.027323
+    17   9728.0  440.513191  281.291575  290.027323
-    18  10240.0  450.109870  286.767793  290.496460
+    18  10240.0  449.287041  285.767451  289.129408
-    19  10752.0  426.525614  247.172406  290.594591
+    19  10752.0  429.364408  246.699797  289.941565
-    20  11264.0  427.071098  245.760001  286.676558
+    20  11264.0  424.389312  245.536784  287.591490
-    21  11776.0  423.089806  249.667843  288.981596
+    21  11776.0  421.198220  249.888595  288.686414
-    22  12288.0  419.504980  254.893699  294.323369
+    22  12288.0  417.722367  253.796902  294.617366
-    23  12800.0  414.016170  253.674644  289.538159
+    23  12800.0  415.135142  253.674644  289.811310
-    24  13312.0  411.181478  252.759501  289.916513
+    24  13312.0  409.599999  251.962147  289.129403
     25  13824.0  404.604870  257.190689  292.056329
-    26  14336.0  393.665895  254.485198  286.719986
+    26  14336.0  395.930964  253.734520  287.438588
-    27  14848.0  384.829370  257.665934  289.246765
+    27  14848.0  384.829370  255.999999  288.544136
-    28  15360.0  373.874218  257.970599  286.433562
+    28  15360.0  376.932517  259.422943  289.583654
-    29  15872.0  371.274849  261.986243  289.679087
+    29  15872.0  367.336555  262.708969  290.784741
 
 
 
@@ -339,7 +339,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  12.368 seconds)
+   **Total running time of the script:** ( 2 minutes  12.916 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
 =================
-**13:22.195** total execution time for **getting-started_tutorials** files:
+**13:26.728** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:06.796 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:05.749 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:21.705 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:21.745 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.368 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.916 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:40.829 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:45.824 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.496 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.493 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -325,22 +325,22 @@ 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   76.800002   76.800002
+3       32768.0   63.999998   76.800002
 4       65536.0  127.999995  127.999995
 5      131072.0  219.428568  219.428568
-6      262144.0  384.000001  384.000001
+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
 10    4194304.0  780.190482  780.190482
 11    8388608.0  812.429770  812.429770
 12   16777216.0  833.084721  833.084721
-13   33554432.0  842.004273  843.811163
+13   33554432.0  842.004273  842.004273
 14   67108864.0  847.448255  848.362445
 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  40.829 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  45.824 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

@@ -369,17 +369,17 @@ We will then compare its performance against (1) <code class="code docutils lite
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>softmax-performance:
           N      Triton  Torch (native)  Torch (jit)
-0     256.0  512.000001      546.133347   186.181817
+0     256.0  512.000001      546.133347   188.321838
-1     384.0  614.400016      585.142862   153.600004
+1     384.0  585.142862      558.545450   153.600004
-2     512.0  655.360017      606.814814   156.038096
+2     512.0  655.360017      606.814814   154.566038
 3     640.0  706.206879      640.000002   160.000000
 4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
-93  12160.0  814.058574      406.179533   199.140227
+93  12160.0  814.058574      405.333344   198.834951
-94  12288.0  814.111783      415.222812   199.399583
+94  12288.0  814.111783      415.222812   199.096718
-95  12416.0  814.163950      412.149375   198.954424
+95  12416.0  814.163950      411.296057   198.755369
-96  12544.0  814.214963      412.971190   199.209928
+96  12544.0  814.214963      412.546756   198.913776
-97  12672.0  814.265046      412.097543   199.264875
+97  12672.0  814.265046      412.097543   199.069228
 
 [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  21.705 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  21.745 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

@@ -564,42 +564,42 @@ 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  ...   3.276800              2.978909
+0    256.0   2.730667  ...   2.978909              2.978909
-1    384.0   7.372800  ...   8.507077              8.507077
+1    384.0   7.372800  ...   7.899428              8.507077
-2    512.0  14.563555  ...  16.384000             16.384000
+2    512.0  14.563555  ...  16.384000             15.420235
-3    640.0  23.272727  ...  24.380953             24.380953
+3    640.0  22.260869  ...  24.380953             24.380953
 4    768.0  32.768000  ...  34.028308             34.028308
-5    896.0  39.025776  ...  40.140799             39.025776
+5    896.0  39.025776  ...  40.140799             37.971025
-6   1024.0  51.150050  ...  52.428801             52.428801
+6   1024.0  49.932191  ...  52.428801             52.428801
 7   1152.0  45.242181  ...  46.656000             46.656000
 8   1280.0  51.200001  ...  56.888887             56.888887
 9   1408.0  64.138541  ...  67.305878             66.485074
 10  1536.0  80.430545  ...  79.526831             78.643199
-11  1664.0  62.929456  ...  62.492442             62.061463
+11  1664.0  62.929456  ...  62.061463             62.492442
-12  1792.0  72.512412  ...  72.047592             71.588687
+12  1792.0  72.512412  ...  71.588687             72.047592
-13  1920.0  68.776119  ...  70.530615             69.818184
+13  1920.0  69.467336  ...  70.172588             70.172588
-14  2048.0  73.584279  ...  76.608294             76.608294
+14  2048.0  73.262953  ...  76.608294             76.260072
-15  2176.0  83.500614  ...  85.998493             85.632545
+15  2176.0  83.155572  ...  85.998493             85.998493
-16  2304.0  68.643310  ...  76.809875             76.563695
+16  2304.0  68.643310  ...  76.809875             76.809875
-17  2432.0  71.487187  ...  83.119713             85.134737
+17  2432.0  71.487187  ...  74.521127             84.877538
-18  2560.0  78.019048  ...  80.511054             80.511054
+18  2560.0  77.833728  ...  81.108913             80.808877
-19  2688.0  83.737433  ...  89.888756             89.464755
+19  2688.0  82.823267  ...  89.676257             89.464755
-20  2816.0  82.602666  ...  82.759409             82.602666
+20  2816.0  80.617762  ...  82.602666             83.392363
-21  2944.0  82.102191  ...  82.509987             82.784108
+21  2944.0  81.832567  ...  82.102191             82.102191
-22  3072.0  82.661468  ...  87.924073             85.275760
+22  3072.0  82.121977  ...  88.335577             86.911900
-23  3200.0  84.993363  ...  95.665176             94.674553
+23  3200.0  78.717759  ...  91.559367             92.753621
-24  3328.0  82.939284  ...  83.130825             84.596116
+24  3328.0  79.990330  ...  83.130825             83.905938
-25  3456.0  81.766291  ...  91.097818             84.597660
+25  3456.0  81.724858  ...  91.304157             90.892410
-26  3584.0  84.905939  ...  93.759530             87.296493
+26  3584.0  83.101104  ...  91.563533             96.579370
-27  3712.0  84.159518  ...  86.341700             86.867254
+27  3712.0  85.748791  ...  86.045381             91.901879
-28  3840.0  84.874902  ...  92.236860             84.552479
+28  3840.0  80.313725  ...  86.265212             91.322872
-29  3968.0  92.302520  ...  84.098250             90.791620
+29  3968.0  86.911637  ...  90.221021             83.922926
-30  4096.0  86.426548  ...  85.434583             91.180520
+30  4096.0  92.755862  ...  88.301134             82.342167
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  6.796 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  5.749 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  0.496 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.493 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

@@ -194,36 +194,36 @@ to download the full example code</p>
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>layer-norm-backward:
           N      Triton       Torch        Apex
-0    1024.0  311.088617   98.303995  307.200008
+0    1024.0  307.200008   95.255819  292.571431
-1    1536.0  347.773587  134.540150  344.523365
+1    1536.0  347.773587  135.529409  344.523365
-2    2048.0  423.724127  161.684218  325.509933
+2    2048.0  420.102553  162.217818  325.509933
-3    2560.0  458.507457  181.775141  326.808501
+3    2560.0  451.764698  183.402991  330.322572
-4    3072.0  511.999982  192.501302  319.168834
+4    3072.0  515.580429  191.501303  317.793096
-5    3584.0  551.384634  208.271186  311.652167
+5    3584.0  547.872604  207.768111  311.652167
-6    4096.0  568.231237  220.412561  299.707322
+6    4096.0  564.965515  220.907859  301.546004
-7    4608.0  507.302750  232.825259  286.507772
+7    4608.0  504.986315  232.825259  288.751954
-8    5120.0  529.655159  242.845844  284.444444
+8    5120.0  531.948056  242.845844  285.104413
-9    5632.0  545.032265  243.545956  290.060087
+9    5632.0  545.032265  243.107920  290.060087
-10   6144.0  548.163546  248.661056  286.879370
+10   6144.0  548.163546  250.349744  286.879370
-11   6656.0  534.260858  256.000009  285.767438
+11   6656.0  537.858601  254.775119  285.767438
-12   7168.0  507.469040  260.654538  286.242939
+12   7168.0  508.970395  256.000002  279.726817
-13   7680.0  481.253256  262.564106  279.272719
+13   7680.0  485.052616  263.690977  278.009056
-14   8192.0  462.607053  267.130429  284.939124
+14   8192.0  462.607053  264.258058  280.068380
-15   8704.0  417.791980  267.815384  285.377055
+15   8704.0  417.791980  263.757583  282.291896
-16   9216.0  431.157889  272.394084  288.751954
+16   9216.0  430.319054  270.727053  286.879380
-17   9728.0  439.683593  280.615388  290.027323
+17   9728.0  440.513191  281.291575  290.027323
-18  10240.0  450.109870  286.767793  290.496460
+18  10240.0  449.287041  285.767451  289.129408
-19  10752.0  426.525614  247.172406  290.594591
+19  10752.0  429.364408  246.699797  289.941565
-20  11264.0  427.071098  245.760001  286.676558
+20  11264.0  424.389312  245.536784  287.591490
-21  11776.0  423.089806  249.667843  288.981596
+21  11776.0  421.198220  249.888595  288.686414
-22  12288.0  419.504980  254.893699  294.323369
+22  12288.0  417.722367  253.796902  294.617366
-23  12800.0  414.016170  253.674644  289.538159
+23  12800.0  415.135142  253.674644  289.811310
-24  13312.0  411.181478  252.759501  289.916513
+24  13312.0  409.599999  251.962147  289.129403
 25  13824.0  404.604870  257.190689  292.056329
-26  14336.0  393.665895  254.485198  286.719986
+26  14336.0  395.930964  253.734520  287.438588
-27  14848.0  384.829370  257.665934  289.246765
+27  14848.0  384.829370  255.999999  288.544136
-28  15360.0  373.874218  257.970599  286.433562
+28  15360.0  376.932517  259.422943  289.583654
-29  15872.0  371.274849  261.986243  289.679087
+29  15872.0  367.336555  262.708969  290.784741
 </pre></div>
 </div>
 <div class="line-block">
@@ -487,7 +487,7 @@ 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> ( 2 minutes  12.368 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  12.916 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>13:22.195</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:26.728</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>06:06.796</p></td>
+<td><p>06:05.749</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><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>03:21.705</p></td>
+<td><p>03:21.745</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><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>02:12.368</p></td>
+<td><p>02:12.916</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>01:40.829</p></td>
+<td><p>01:45.824</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>00:00.496</p></td>
+<td><p>00:00.493</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: 8adf1e108d72a646364ef53eb334367b
+config: 49e46a4dfdc685c585b0e8121d706820
 tags: 645f666f9bcd5a90fca523b33c5a78b7