[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: d87e0e91ea31c1a946fae22fbba13feb
+config: c16e8b19f5cc6e0fa6ea8368ac598835
 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   63.999998
     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
     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  842.004273
+    13   33554432.0  842.004273  843.811163
     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  40.635 seconds)
+   **Total running time of the script:** ( 1 minutes  45.983 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   192.752942
+    0     256.0  512.000001      546.133347   190.511628
     1     384.0  614.400016      585.142862   153.600004
     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   198.530610
-    94  12288.0  814.111783      415.661740   198.895304
-    95  12416.0  814.163950      412.149375   198.457532
-    96  12544.0  814.214963      412.971190   198.618504
-    97  12672.0  814.265046      411.679167   198.776477
+    93  12160.0  814.058574      405.755985   198.834951
+    94  12288.0  814.111783      415.661740   199.096718
+    95  12416.0  814.163950      411.722274   198.755369
+    96  12544.0  814.214963      412.971190   198.913776
+    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  21.561 seconds)
+   **Total running time of the script:** ( 3 minutes  22.256 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              3.276800
-    1    384.0   7.372800  ...   7.899428              7.899428
-    2    512.0  14.563555  ...  16.384000             16.384000
+    0    256.0   2.978909  ...   3.276800              2.978909
+    1    384.0   7.372800  ...   8.507077              7.899428
+    2    512.0  14.563555  ...  16.384000             15.420235
     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
-    6   1024.0  51.150050  ...  52.428801             52.428801
+    6   1024.0  51.150050  ...  53.773130             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
-    12  1792.0  72.512412  ...  72.047592             72.047592
-    13  1920.0  68.776119  ...  70.172588             69.818184
-    14  2048.0  73.262953  ...  76.608294             76.260072
-    15  2176.0  83.155572  ...  85.998493             85.269692
-    16  2304.0  68.446623  ...  76.319081             76.319081
-    17  2432.0  71.487187  ...  74.918570             84.621881
-    18  2560.0  77.833728  ...  81.108913             80.908642
-    19  2688.0  83.737433  ...  89.888756             89.676257
-    20  2816.0  82.290955  ...  82.916747             82.602666
-    21  2944.0  82.102191  ...  79.865439             82.921853
-    22  3072.0  81.355034  ...  87.516392             86.184329
-    23  3200.0  83.224970  ...  90.909090             89.260810
-    24  3328.0  80.798314  ...  83.226931             84.596116
-    25  3456.0  82.266905  ...  90.382926             90.994998
-    26  3584.0  84.111686  ...  92.600816             94.448944
-    27  3712.0  85.528545  ...  85.163978             88.170647
-    28  3840.0  80.197243  ...  86.197974             91.473945
-    29  3968.0  85.991957  ...  90.791620             85.093402
-    30  4096.0  92.852115  ...  82.493991             82.241256
+    10  1536.0  79.526831  ...  79.526831             78.643199
+    11  1664.0  62.929456  ...  62.492442             62.492442
+    12  1792.0  72.983276  ...  72.047592             72.047592
+    13  1920.0  69.467336  ...  70.172588             69.818184
+    14  2048.0  73.262953  ...  76.608294             76.608294
+    15  2176.0  83.500614  ...  86.367588             85.632545
+    16  2304.0  68.446623  ...  76.809875             76.809875
+    17  2432.0  71.396351  ...  83.614477             85.393507
+    18  2560.0  78.019048  ...  81.108913             80.709358
+    19  2688.0  83.737433  ...  89.676257             89.676257
+    20  2816.0  82.135981  ...  82.916747             82.916747
+    21  2944.0  82.237674  ...  82.237674             82.102191
+    22  3072.0  80.089253  ...  88.473602             88.335577
+    23  3200.0  83.116885  ...  95.238096             95.380032
+    24  3328.0  82.369902  ...  84.003845             84.200347
+    25  3456.0  80.220468  ...  86.503829             87.536988
+    26  3584.0  86.457107  ...  98.268190             98.268190
+    27  3712.0  80.757757  ...  87.783251             84.946722
+    28  3840.0  83.027026  ...  90.574940             84.613126
+    29  3968.0  87.976885  ...  85.212248             87.035620
+    30  4096.0  91.992956  ...  92.755862             86.092193
 
     [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  0.809 seconds)
+   **Total running time of the script:** ( 6 minutes  2.552 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  0.493 seconds)
+   **Total running time of the script:** ( 0 minutes  0.483 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
-    1    1536.0  347.773587  134.050910  344.523365
-    2    2048.0  420.102553  161.684218  334.367350
-    3    2560.0  455.111129  181.775141  328.556154
-    4    3072.0  511.999982  192.501302  321.956335
-    5    3584.0  547.872604  208.271186  311.652167
-    6    4096.0  568.231237  220.412561  297.890900
-    7    4608.0  504.986315  233.316456  287.251954
-    8    5120.0  527.381977  242.845844  285.104413
-    9    5632.0  545.032265  243.545956  289.438969
-    10   6144.0  546.133354  248.661056  286.322318
-    11   6656.0  534.260858  256.000009  286.279570
-    12   7168.0  505.976473  260.654538  286.242939
-    13   7680.0  482.513091  262.564106  279.272719
-    14   8192.0  463.698115  267.493874  284.526763
-    15   8704.0  418.629245  267.815384  284.987724
-    16   9216.0  432.845409  272.394084  288.751954
-    17   9728.0  438.857162  280.446849  290.027323
-    18  10240.0  449.287041  286.767793  290.840246
-    19  10752.0  426.525614  247.172406  290.922209
-    20  11264.0  427.071098  245.760001  286.676558
-    21  11776.0  423.724129  249.888595  288.981596
-    22  12288.0  420.102570  254.673582  294.617366
-    23  12800.0  413.458944  253.674644  288.450715
-    24  13312.0  411.711355  252.759501  289.916513
-    25  13824.0  405.594132  257.390218  292.056329
-    26  14336.0  395.021816  254.297107  286.719986
-    27  14848.0  386.498925  257.665934  289.246765
-    28  15360.0  373.117425  257.970599  287.326580
-    29  15872.0  371.274849  261.806182  289.899545
+    0    1024.0  307.200008   99.902435  311.088617
+    1    1536.0  351.085717  133.083026  341.333333
+    2    2048.0  423.724127  159.067963  321.254900
+    3    2560.0  451.764698  182.857144  323.368411
+    4    3072.0  515.580429  191.501303  319.168834
+    5    3584.0  551.384634  208.271186  310.527060
+    6    4096.0  568.231237  220.412561  299.707322
+    7    4608.0  504.986315  232.825259  286.507772
+    8    5120.0  531.948056  244.294240  286.433562
+    9    5632.0  542.843364  244.869560  291.939522
+    10   6144.0  552.269672  251.631408  288.000001
+    11   6656.0  537.858601  255.590406  286.793541
+    12   7168.0  516.612607  254.485198  278.368936
+    13   7680.0  487.619051  266.743841  284.884090
+    14   8192.0  467.002371  257.003920  276.912679
+    15   8704.0  418.629245  267.815384  286.158893
+    16   9216.0  432.000001  273.404206  289.887291
+    17   9728.0  442.181815  280.615388  289.667485
+    18  10240.0  448.467168  287.102804  290.840246
+    19  10752.0  428.651173  246.464170  289.616170
+    20  11264.0  427.746848  246.432094  286.980888
+    21  11776.0  421.826879  249.888595  288.981596
+    22  12288.0  417.131525  254.893699  294.617366
+    23  12800.0  415.696898  253.674644  290.359162
+    24  13312.0  410.125805  252.559690  289.653667
+    25  13824.0  402.640783  257.190689  292.056329
+    26  14336.0  396.387109  255.240352  289.129416
+    27  14848.0  383.174202  257.293872  287.844912
+    28  15360.0  374.253788  258.513318  286.879376
+    29  15872.0  368.402336  262.347108  290.120338
 
 
 
@@ -339,7 +339,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  12.386 seconds)
+   **Total running time of the script:** ( 2 minutes  11.369 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
 =================
-**13:15.884** total execution time for **getting-started_tutorials** files:
+**13:22.642** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:00.809 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:02.552 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:21.561 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:22.256 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.386 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:11.369 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:40.635 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:45.983 | 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 |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.483 | 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   63.999998
 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
 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  842.004273
+13   33554432.0  842.004273  843.811163
 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  40.635 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  45.983 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   192.752942
+0     256.0  512.000001      546.133347   190.511628
 1     384.0  614.400016      585.142862   153.600004
 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   198.530610
-94  12288.0  814.111783      415.661740   198.895304
-95  12416.0  814.163950      412.149375   198.457532
-96  12544.0  814.214963      412.971190   198.618504
-97  12672.0  814.265046      411.679167   198.776477
+93  12160.0  814.058574      405.755985   198.834951
+94  12288.0  814.111783      415.661740   199.096718
+95  12416.0  814.163950      411.722274   198.755369
+96  12544.0  814.214963      412.971190   198.913776
+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  21.561 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  22.256 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              3.276800
-1    384.0   7.372800  ...   7.899428              7.899428
-2    512.0  14.563555  ...  16.384000             16.384000
+0    256.0   2.978909  ...   3.276800              2.978909
+1    384.0   7.372800  ...   8.507077              7.899428
+2    512.0  14.563555  ...  16.384000             15.420235
 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
-6   1024.0  51.150050  ...  52.428801             52.428801
+6   1024.0  51.150050  ...  53.773130             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
-12  1792.0  72.512412  ...  72.047592             72.047592
-13  1920.0  68.776119  ...  70.172588             69.818184
-14  2048.0  73.262953  ...  76.608294             76.260072
-15  2176.0  83.155572  ...  85.998493             85.269692
-16  2304.0  68.446623  ...  76.319081             76.319081
-17  2432.0  71.487187  ...  74.918570             84.621881
-18  2560.0  77.833728  ...  81.108913             80.908642
-19  2688.0  83.737433  ...  89.888756             89.676257
-20  2816.0  82.290955  ...  82.916747             82.602666
-21  2944.0  82.102191  ...  79.865439             82.921853
-22  3072.0  81.355034  ...  87.516392             86.184329
-23  3200.0  83.224970  ...  90.909090             89.260810
-24  3328.0  80.798314  ...  83.226931             84.596116
-25  3456.0  82.266905  ...  90.382926             90.994998
-26  3584.0  84.111686  ...  92.600816             94.448944
-27  3712.0  85.528545  ...  85.163978             88.170647
-28  3840.0  80.197243  ...  86.197974             91.473945
-29  3968.0  85.991957  ...  90.791620             85.093402
-30  4096.0  92.852115  ...  82.493991             82.241256
+10  1536.0  79.526831  ...  79.526831             78.643199
+11  1664.0  62.929456  ...  62.492442             62.492442
+12  1792.0  72.983276  ...  72.047592             72.047592
+13  1920.0  69.467336  ...  70.172588             69.818184
+14  2048.0  73.262953  ...  76.608294             76.608294
+15  2176.0  83.500614  ...  86.367588             85.632545
+16  2304.0  68.446623  ...  76.809875             76.809875
+17  2432.0  71.396351  ...  83.614477             85.393507
+18  2560.0  78.019048  ...  81.108913             80.709358
+19  2688.0  83.737433  ...  89.676257             89.676257
+20  2816.0  82.135981  ...  82.916747             82.916747
+21  2944.0  82.237674  ...  82.237674             82.102191
+22  3072.0  80.089253  ...  88.473602             88.335577
+23  3200.0  83.116885  ...  95.238096             95.380032
+24  3328.0  82.369902  ...  84.003845             84.200347
+25  3456.0  80.220468  ...  86.503829             87.536988
+26  3584.0  86.457107  ...  98.268190             98.268190
+27  3712.0  80.757757  ...  87.783251             84.946722
+28  3840.0  83.027026  ...  90.574940             84.613126
+29  3968.0  87.976885  ...  85.212248             87.035620
+30  4096.0  91.992956  ...  92.755862             86.092193
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  0.809 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  2.552 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  0.493 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.483 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
-1    1536.0  347.773587  134.050910  344.523365
-2    2048.0  420.102553  161.684218  334.367350
-3    2560.0  455.111129  181.775141  328.556154
-4    3072.0  511.999982  192.501302  321.956335
-5    3584.0  547.872604  208.271186  311.652167
-6    4096.0  568.231237  220.412561  297.890900
-7    4608.0  504.986315  233.316456  287.251954
-8    5120.0  527.381977  242.845844  285.104413
-9    5632.0  545.032265  243.545956  289.438969
-10   6144.0  546.133354  248.661056  286.322318
-11   6656.0  534.260858  256.000009  286.279570
-12   7168.0  505.976473  260.654538  286.242939
-13   7680.0  482.513091  262.564106  279.272719
-14   8192.0  463.698115  267.493874  284.526763
-15   8704.0  418.629245  267.815384  284.987724
-16   9216.0  432.845409  272.394084  288.751954
-17   9728.0  438.857162  280.446849  290.027323
-18  10240.0  449.287041  286.767793  290.840246
-19  10752.0  426.525614  247.172406  290.922209
-20  11264.0  427.071098  245.760001  286.676558
-21  11776.0  423.724129  249.888595  288.981596
-22  12288.0  420.102570  254.673582  294.617366
-23  12800.0  413.458944  253.674644  288.450715
-24  13312.0  411.711355  252.759501  289.916513
-25  13824.0  405.594132  257.390218  292.056329
-26  14336.0  395.021816  254.297107  286.719986
-27  14848.0  386.498925  257.665934  289.246765
-28  15360.0  373.117425  257.970599  287.326580
-29  15872.0  371.274849  261.806182  289.899545
+0    1024.0  307.200008   99.902435  311.088617
+1    1536.0  351.085717  133.083026  341.333333
+2    2048.0  423.724127  159.067963  321.254900
+3    2560.0  451.764698  182.857144  323.368411
+4    3072.0  515.580429  191.501303  319.168834
+5    3584.0  551.384634  208.271186  310.527060
+6    4096.0  568.231237  220.412561  299.707322
+7    4608.0  504.986315  232.825259  286.507772
+8    5120.0  531.948056  244.294240  286.433562
+9    5632.0  542.843364  244.869560  291.939522
+10   6144.0  552.269672  251.631408  288.000001
+11   6656.0  537.858601  255.590406  286.793541
+12   7168.0  516.612607  254.485198  278.368936
+13   7680.0  487.619051  266.743841  284.884090
+14   8192.0  467.002371  257.003920  276.912679
+15   8704.0  418.629245  267.815384  286.158893
+16   9216.0  432.000001  273.404206  289.887291
+17   9728.0  442.181815  280.615388  289.667485
+18  10240.0  448.467168  287.102804  290.840246
+19  10752.0  428.651173  246.464170  289.616170
+20  11264.0  427.746848  246.432094  286.980888
+21  11776.0  421.826879  249.888595  288.981596
+22  12288.0  417.131525  254.893699  294.617366
+23  12800.0  415.696898  253.674644  290.359162
+24  13312.0  410.125805  252.559690  289.653667
+25  13824.0  402.640783  257.190689  292.056329
+26  14336.0  396.387109  255.240352  289.129416
+27  14848.0  383.174202  257.293872  287.844912
+28  15360.0  374.253788  258.513318  286.879376
+29  15872.0  368.402336  262.347108  290.120338
 </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  12.386 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  11.369 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>13:15.884</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:22.642</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>06:00.809</p></td>
+<td><p>06:02.552</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>03:21.561</p></td>
+<td><p>03:22.256</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>02:12.386</p></td>
+<td><p>02:11.369</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>01:40.635</p></td>
+<td><p>01:45.983</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>00:00.493</p></td>
+<td><p>00:00.483</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: 4f0a2db0634bd6784bdd49e2ef2b0b57
+config: 0042334a895e9de1ea19b1b1d8c0023c
 tags: 645f666f9bcd5a90fca523b33c5a78b7