[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: 23dabe2cb77fc97d70bf1e93da31ad39
+config: c2a30e9b7ff7a838298eb8c46d23fa63
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -234,8 +234,8 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
                size      Triton       Torch
     0        4096.0    9.600000    9.600000
     1        8192.0   19.200000   19.200000
-    2       16384.0   31.999999   31.999999
+    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
@@ -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  46.974 seconds)
+   **Total running time of the script:** ( 1 minutes  37.409 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

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

@@ -278,16 +278,16 @@ 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   188.321838
+    0     256.0  512.000001      546.133347   186.181817
-    1     384.0  585.142862      585.142862   151.703707
+    1     384.0  585.142862      585.142862   153.600004
-    2     512.0  655.360017      606.814814   156.038096
+    2     512.0  655.360017      606.814814   154.566038
-    3     640.0  682.666684      640.000002   160.000000
+    3     640.0  682.666684      620.606056   160.000000
-    4     768.0  722.823517      646.736871   163.839992
+    4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
     93  12160.0  814.058574      405.755985   198.936606
-    94  12288.0  814.111783      415.222812   199.197579
+    94  12288.0  815.800825      415.661740   199.298541
-    95  12416.0  814.163950      412.149375   198.954424
+    95  12416.0  814.163950      411.722274   198.854847
-    96  12544.0  814.214963      412.971190   199.111113
+    96  12544.0  814.214963      412.546756   199.061730
     97  12672.0  814.265046      412.097543   199.167004
 
     [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  28.936 seconds)
+   **Total running time of the script:** ( 3 minutes  27.320 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   2.730667  ...   3.276800              2.978909
+    0    256.0   2.730667  ...   2.978909              2.978909
-    1    384.0   7.372800  ...   7.899428              8.507077
+    1    384.0   7.372800  ...   7.899428              7.899428
-    2    512.0  14.563555  ...  16.384000             16.384000
+    2    512.0  14.563555  ...  15.420235             16.384000
     3    640.0  22.260869  ...  24.380953             24.380953
-    4    768.0  32.768000  ...  35.389441             34.028308
+    4    768.0  32.768000  ...  34.028308             34.028308
-    5    896.0  37.971025  ...  40.140799             40.140799
+    5    896.0  37.971025  ...  41.321411             40.140799
-    6   1024.0  49.932191  ...  53.773130             53.773130
+    6   1024.0  49.932191  ...  53.773130             52.428801
-    7   1152.0  45.242181  ...  48.161033             47.396572
+    7   1152.0  44.566925  ...  48.161033             47.396572
-    8   1280.0  51.200001  ...  58.514284             57.690139
+    8   1280.0  51.200001  ...  57.690139             57.690139
-    9   1408.0  64.138541  ...  69.009825             69.009825
+    9   1408.0  64.138541  ...  69.009825             68.147202
-    10  1536.0  79.526831  ...  80.430545             80.430545
+    10  1536.0  80.430545  ...  80.430545             79.526831
     11  1664.0  62.929456  ...  63.372618             62.929456
-    12  1792.0  72.983276  ...  63.142831             62.790080
+    12  1792.0  72.983276  ...  63.499573             62.790080
-    13  1920.0  68.776119  ...  71.626943             71.257735
+    13  1920.0  69.120002  ...  71.626943             70.892307
-    14  2048.0  73.584279  ...  78.398206             78.033565
+    14  2048.0  73.262953  ...  78.033565             78.033565
     15  2176.0  83.155572  ...  87.115360             86.739860
-    16  2304.0  68.446623  ...  77.810656             77.558029
+    16  2304.0  68.446623  ...  77.558029             77.307030
-    17  2432.0  71.125224  ...  75.726318             75.320281
+    17  2432.0  71.125224  ...  75.726318             74.918570
-    18  2560.0  77.833728  ...  82.125311             81.715711
+    18  2560.0  77.833728  ...  82.331658             81.715711
-    19  2688.0  83.369354  ...  90.532356             90.748936
+    19  2688.0  83.369354  ...  91.404957             91.185232
-    20  2816.0  80.916902  ...  83.552120             83.552120
+    20  2816.0  79.733474  ...  83.873477             83.392363
-    21  2944.0  82.373605  ...  83.617504             83.617504
+    21  2944.0  82.102191  ...  83.758038             84.182483
-    22  3072.0  81.707223  ...  87.651868             89.593522
+    22  3072.0  81.296638  ...  88.473602             87.516392
-    23  3200.0  85.219705  ...  96.385543             96.385543
+    23  3200.0  79.750779  ...  96.168294             95.952022
-    24  3328.0  82.275764  ...  86.011103             85.703924
+    24  3328.0  82.939284  ...  86.528001             85.602017
-    25  3456.0  81.890873  ...  92.455926             92.138932
+    25  3456.0  82.688790  ...  92.455926             86.689860
-    26  3584.0  86.623693  ...  89.290361             94.250936
+    26  3584.0  86.291162  ...  88.152348             94.250936
-    27  3712.0  85.675250  ...  88.092894             84.874549
+    27  3712.0  85.675250  ...  87.706180             87.246590
-    28  3840.0  84.679936  ...  92.468225             85.136259
+    28  3840.0  81.079177  ...  86.875096             91.398346
-    29  3968.0  90.724116  ...  84.974886             90.522206
+    29  3968.0  87.035620  ...  89.525997             84.917596
-    30  4096.0  90.996029  ...  87.438257             92.309303
+    30  4096.0  88.243079  ...  85.161847             91.616198
 
     [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  10.290 seconds)
+   **Total running time of the script:** ( 6 minutes  2.101 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  0.012 seconds)
+   **Total running time of the script:** ( 0 minutes  0.013 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  361.411758   99.902435  315.076934
+    0    1024.0  356.173905   98.303995  296.096389
-    1    1536.0  409.599994  134.050910  344.523365
+    1    1536.0  409.599994  132.604320  341.333333
-    2    2048.0  496.484863  159.067963  323.368435
+    2    2048.0  491.520012  161.684218  336.657521
-    3    2560.0  461.954908  182.857144  325.079368
+    3    2560.0  461.954908  182.857144  330.322572
-    4    3072.0  519.211251  191.501303  320.556515
+    4    3072.0  519.211251  191.501303  319.168834
-    5    3584.0  554.941930  207.768111  310.527060
+    5    3584.0  558.545477  207.768111  310.527060
-    6    4096.0  564.965515  220.907859  301.546004
+    6    4096.0  564.965515  220.907859  298.796351
-    7    4608.0  502.690905  232.336141  287.251954
+    7    4608.0  502.690905  232.825259  288.751954
-    8    5120.0  529.655159  243.809526  286.433562
+    8    5120.0  529.655159  243.326731  285.767451
-    9    5632.0  542.843364  244.869560  291.310338
+    9    5632.0  545.032265  242.236559  290.060087
-    10   6144.0  550.208948  251.202731  287.438593
+    10   6144.0  550.208948  251.202731  288.563606
-    11   6656.0  534.260858  256.000009  286.793541
+    11   6656.0  530.710976  255.182111  285.257135
-    12   7168.0  510.480705  253.734520  277.919225
+    12   7168.0  512.000004  251.877006  276.134819
-    13   7680.0  487.619051  266.743841  285.325090
+    13   7680.0  483.779539  263.690977  276.756754
-    14   8192.0  468.114289  258.354805  278.087683
+    14   8192.0  465.895721  267.130429  278.876591
-    15   8704.0  415.300208  267.815384  285.377055
+    15   8704.0  414.476194  266.448988  283.440968
-    16   9216.0  430.319054  272.059034  290.267724
+    16   9216.0  428.651187  270.396088  287.625496
-    17   9728.0  438.033784  279.942444  288.950501
+    17   9728.0  438.445087  281.630872  289.667485
-    18  10240.0  445.217381  287.438599  290.840246
+    18  10240.0  444.412281  286.433562  288.112552
-    19  10752.0  427.231788  246.935876  289.941565
+    19  10752.0  427.940303  246.699797  290.267711
-    20  11264.0  427.746848  245.536784  286.372873
+    20  11264.0  427.071098  243.985547  284.564206
-    21  11776.0  419.323436  249.447482  288.981596
+    21  11776.0  421.826879  249.447482  288.981596
-    22  12288.0  415.954875  254.673582  294.323369
+    22  12288.0  418.314886  254.015505  294.323369
-    23  12800.0  410.695192  254.094291  289.811310
+    23  12800.0  413.458944  253.256381  289.538159
-    24  13312.0  410.125805  252.559690  289.391298
+    24  13312.0  409.075539  252.559690  290.443638
-    25  13824.0  404.604870  257.190689  291.799461
+    25  13824.0  403.620451  257.590056  292.056329
-    26  14336.0  396.844280  256.000002  289.129416
+    26  14336.0  400.074432  255.051144  288.160801
-    27  14848.0  386.080180  257.665934  289.012175
+    27  14848.0  384.414233  257.665934  289.717061
-    28  15360.0  378.869469  258.332158  287.550706
+    28  15360.0  378.092318  259.971797  288.225185
-    29  15872.0  372.363640  261.626369  290.562936
+    29  15872.0  370.913333  262.166551  290.562936
 
 
 
@@ -339,7 +339,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  14.494 seconds)
+   **Total running time of the script:** ( 2 minutes  14.528 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
 =================
-**13:40.705** total execution time for **getting-started_tutorials** files:
+**13:21.371** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:10.290 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:02.101 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:28.936 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:27.320 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:14.494 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:14.528 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:46.974 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:37.409 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.012 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.013 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -324,8 +324,8 @@ for different problem sizes.</p>
            size      Triton       Torch
 0        4096.0    9.600000    9.600000
 1        8192.0   19.200000   19.200000
-2       16384.0   31.999999   31.999999
+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
@@ -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  46.974 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  37.409 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

@@ -369,16 +369,16 @@ 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   188.321838
+0     256.0  512.000001      546.133347   186.181817
-1     384.0  585.142862      585.142862   151.703707
+1     384.0  585.142862      585.142862   153.600004
-2     512.0  655.360017      606.814814   156.038096
+2     512.0  655.360017      606.814814   154.566038
-3     640.0  682.666684      640.000002   160.000000
+3     640.0  682.666684      620.606056   160.000000
-4     768.0  722.823517      646.736871   163.839992
+4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
 93  12160.0  814.058574      405.755985   198.936606
-94  12288.0  814.111783      415.222812   199.197579
+94  12288.0  815.800825      415.661740   199.298541
-95  12416.0  814.163950      412.149375   198.954424
+95  12416.0  814.163950      411.722274   198.854847
-96  12544.0  814.214963      412.971190   199.111113
+96  12544.0  814.214963      412.546756   199.061730
 97  12672.0  814.265046      412.097543   199.167004
 
 [98 rows x 4 columns]
@@ -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  28.936 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  27.320 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   2.730667  ...   3.276800              2.978909
+0    256.0   2.730667  ...   2.978909              2.978909
-1    384.0   7.372800  ...   7.899428              8.507077
+1    384.0   7.372800  ...   7.899428              7.899428
-2    512.0  14.563555  ...  16.384000             16.384000
+2    512.0  14.563555  ...  15.420235             16.384000
 3    640.0  22.260869  ...  24.380953             24.380953
-4    768.0  32.768000  ...  35.389441             34.028308
+4    768.0  32.768000  ...  34.028308             34.028308
-5    896.0  37.971025  ...  40.140799             40.140799
+5    896.0  37.971025  ...  41.321411             40.140799
-6   1024.0  49.932191  ...  53.773130             53.773130
+6   1024.0  49.932191  ...  53.773130             52.428801
-7   1152.0  45.242181  ...  48.161033             47.396572
+7   1152.0  44.566925  ...  48.161033             47.396572
-8   1280.0  51.200001  ...  58.514284             57.690139
+8   1280.0  51.200001  ...  57.690139             57.690139
-9   1408.0  64.138541  ...  69.009825             69.009825
+9   1408.0  64.138541  ...  69.009825             68.147202
-10  1536.0  79.526831  ...  80.430545             80.430545
+10  1536.0  80.430545  ...  80.430545             79.526831
 11  1664.0  62.929456  ...  63.372618             62.929456
-12  1792.0  72.983276  ...  63.142831             62.790080
+12  1792.0  72.983276  ...  63.499573             62.790080
-13  1920.0  68.776119  ...  71.626943             71.257735
+13  1920.0  69.120002  ...  71.626943             70.892307
-14  2048.0  73.584279  ...  78.398206             78.033565
+14  2048.0  73.262953  ...  78.033565             78.033565
 15  2176.0  83.155572  ...  87.115360             86.739860
-16  2304.0  68.446623  ...  77.810656             77.558029
+16  2304.0  68.446623  ...  77.558029             77.307030
-17  2432.0  71.125224  ...  75.726318             75.320281
+17  2432.0  71.125224  ...  75.726318             74.918570
-18  2560.0  77.833728  ...  82.125311             81.715711
+18  2560.0  77.833728  ...  82.331658             81.715711
-19  2688.0  83.369354  ...  90.532356             90.748936
+19  2688.0  83.369354  ...  91.404957             91.185232
-20  2816.0  80.916902  ...  83.552120             83.552120
+20  2816.0  79.733474  ...  83.873477             83.392363
-21  2944.0  82.373605  ...  83.617504             83.617504
+21  2944.0  82.102191  ...  83.758038             84.182483
-22  3072.0  81.707223  ...  87.651868             89.593522
+22  3072.0  81.296638  ...  88.473602             87.516392
-23  3200.0  85.219705  ...  96.385543             96.385543
+23  3200.0  79.750779  ...  96.168294             95.952022
-24  3328.0  82.275764  ...  86.011103             85.703924
+24  3328.0  82.939284  ...  86.528001             85.602017
-25  3456.0  81.890873  ...  92.455926             92.138932
+25  3456.0  82.688790  ...  92.455926             86.689860
-26  3584.0  86.623693  ...  89.290361             94.250936
+26  3584.0  86.291162  ...  88.152348             94.250936
-27  3712.0  85.675250  ...  88.092894             84.874549
+27  3712.0  85.675250  ...  87.706180             87.246590
-28  3840.0  84.679936  ...  92.468225             85.136259
+28  3840.0  81.079177  ...  86.875096             91.398346
-29  3968.0  90.724116  ...  84.974886             90.522206
+29  3968.0  87.035620  ...  89.525997             84.917596
-30  4096.0  90.996029  ...  87.438257             92.309303
+30  4096.0  88.243079  ...  85.161847             91.616198
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  10.290 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  2.101 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  0.012 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.013 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  361.411758   99.902435  315.076934
+0    1024.0  356.173905   98.303995  296.096389
-1    1536.0  409.599994  134.050910  344.523365
+1    1536.0  409.599994  132.604320  341.333333
-2    2048.0  496.484863  159.067963  323.368435
+2    2048.0  491.520012  161.684218  336.657521
-3    2560.0  461.954908  182.857144  325.079368
+3    2560.0  461.954908  182.857144  330.322572
-4    3072.0  519.211251  191.501303  320.556515
+4    3072.0  519.211251  191.501303  319.168834
-5    3584.0  554.941930  207.768111  310.527060
+5    3584.0  558.545477  207.768111  310.527060
-6    4096.0  564.965515  220.907859  301.546004
+6    4096.0  564.965515  220.907859  298.796351
-7    4608.0  502.690905  232.336141  287.251954
+7    4608.0  502.690905  232.825259  288.751954
-8    5120.0  529.655159  243.809526  286.433562
+8    5120.0  529.655159  243.326731  285.767451
-9    5632.0  542.843364  244.869560  291.310338
+9    5632.0  545.032265  242.236559  290.060087
-10   6144.0  550.208948  251.202731  287.438593
+10   6144.0  550.208948  251.202731  288.563606
-11   6656.0  534.260858  256.000009  286.793541
+11   6656.0  530.710976  255.182111  285.257135
-12   7168.0  510.480705  253.734520  277.919225
+12   7168.0  512.000004  251.877006  276.134819
-13   7680.0  487.619051  266.743841  285.325090
+13   7680.0  483.779539  263.690977  276.756754
-14   8192.0  468.114289  258.354805  278.087683
+14   8192.0  465.895721  267.130429  278.876591
-15   8704.0  415.300208  267.815384  285.377055
+15   8704.0  414.476194  266.448988  283.440968
-16   9216.0  430.319054  272.059034  290.267724
+16   9216.0  428.651187  270.396088  287.625496
-17   9728.0  438.033784  279.942444  288.950501
+17   9728.0  438.445087  281.630872  289.667485
-18  10240.0  445.217381  287.438599  290.840246
+18  10240.0  444.412281  286.433562  288.112552
-19  10752.0  427.231788  246.935876  289.941565
+19  10752.0  427.940303  246.699797  290.267711
-20  11264.0  427.746848  245.536784  286.372873
+20  11264.0  427.071098  243.985547  284.564206
-21  11776.0  419.323436  249.447482  288.981596
+21  11776.0  421.826879  249.447482  288.981596
-22  12288.0  415.954875  254.673582  294.323369
+22  12288.0  418.314886  254.015505  294.323369
-23  12800.0  410.695192  254.094291  289.811310
+23  12800.0  413.458944  253.256381  289.538159
-24  13312.0  410.125805  252.559690  289.391298
+24  13312.0  409.075539  252.559690  290.443638
-25  13824.0  404.604870  257.190689  291.799461
+25  13824.0  403.620451  257.590056  292.056329
-26  14336.0  396.844280  256.000002  289.129416
+26  14336.0  400.074432  255.051144  288.160801
-27  14848.0  386.080180  257.665934  289.012175
+27  14848.0  384.414233  257.665934  289.717061
-28  15360.0  378.869469  258.332158  287.550706
+28  15360.0  378.092318  259.971797  288.225185
-29  15872.0  372.363640  261.626369  290.562936
+29  15872.0  370.913333  262.166551  290.562936
 </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  14.494 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  14.528 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>13:40.705</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:21.371</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>06:10.290</p></td>
+<td><p>06:02.101</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>03:28.936</p></td>
+<td><p>03:27.320</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>02:14.494</p></td>
+<td><p>02:14.528</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>01:46.974</p></td>
+<td><p>01:37.409</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>00:00.012</p></td>
+<td><p>00:00.013</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: e16a07fadf9ef470b8369966aac76b2c
+config: 959b042a2cc9a21f4df5efdb2f0d6f0a
 tags: 645f666f9bcd5a90fca523b33c5a78b7