[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: bd537efaf126fb307d18a393c4eacf10
+config: c24d43c3d9203b5bc4a3756159b70958
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -235,10 +235,10 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     0        4096.0    9.600000    9.600000
     1        8192.0   19.200000   19.200000
     2       16384.0   38.400001   38.400001
-    3       32768.0   63.999998   63.999998
+    3       32768.0   76.800002   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
@@ -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  42.537 seconds)
+   **Total running time of the script:** ( 1 minutes  36.291 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   190.511628
+    0     256.0  546.133347      546.133347   190.511628
-    1     384.0  614.400016      585.142862   153.600004
+    1     384.0  585.142862      585.142862   153.600004
-    2     512.0  655.360017      606.814814   154.566038
+    2     512.0  655.360017      585.142849   156.038096
-    3     640.0  706.206879      640.000002   160.000000
+    3     640.0  682.666684      640.000002   160.000000
-    4     768.0  722.823517      664.216187   162.754967
+    4     768.0  722.823517      664.216187   163.839992
     ..      ...         ...             ...          ...
-    93  12160.0  814.058574      406.179533   198.733401
+    93  12160.0  814.058574      405.755985   198.936606
     94  12288.0  814.111783      415.661740   198.995960
-    95  12416.0  814.163950      412.149375   198.556711
+    95  12416.0  814.163950      411.722274   198.755369
-    96  12544.0  814.214963      412.971190   198.815254
+    96  12544.0  814.214963      412.971190   198.913776
-    97  12672.0  814.265046      412.097543   198.873965
+    97  12672.0  814.265046      412.516771   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  22.066 seconds)
+   **Total running time of the script:** ( 3 minutes  20.551 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  ...   2.978909              2.978909
+    0    256.0   2.978909  ...   2.978909              3.276800
-    1    384.0   7.372800  ...   8.507077              7.899428
+    1    384.0   7.372800  ...   8.507077              8.507077
     2    512.0  14.563555  ...  16.384000             16.384000
     3    640.0  22.260869  ...  24.380953             24.380953
     4    768.0  32.768000  ...  34.028308             34.028308
-    5    896.0  39.025776  ...  39.025776             39.025776
+    5    896.0  37.971025  ...  40.140799             39.025776
     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
+    10  1536.0  80.430545  ...  79.526831             79.526831
     11  1664.0  62.929456  ...  62.492442             62.061463
-    12  1792.0  72.512412  ...  71.588687             72.047592
+    12  1792.0  72.512412  ...  72.047592             72.047592
-    13  1920.0  69.467336  ...  70.172588             70.172588
+    13  1920.0  69.120002  ...  70.172588             70.530615
-    14  2048.0  73.262953  ...  76.608294             76.608294
+    14  2048.0  73.584279  ...  76.959706             76.608294
-    15  2176.0  83.500614  ...  85.998493             85.998493
+    15  2176.0  83.155572  ...  86.367588             85.269692
-    16  2304.0  68.446623  ...  76.563695             76.319081
+    16  2304.0  68.446623  ...  77.057651             76.076024
-    17  2432.0  71.305746  ...  74.521127             85.134737
+    17  2432.0  71.305746  ...  84.367759             85.134737
-    18  2560.0  78.019048  ...  80.908642             81.108913
+    18  2560.0  78.019048  ...  80.908642             80.709358
-    19  2688.0  82.823267  ...  89.888756             89.464755
+    19  2688.0  83.369354  ...  89.676257             89.254248
-    20  2816.0  83.233226  ...  82.916747             82.759409
+    20  2816.0  79.733474  ...  83.392363             83.233226
-    21  2944.0  81.967162  ...  82.509987             82.237674
+    21  2944.0  81.967162  ...  82.237674             82.102191
-    22  3072.0  82.181572  ...  88.197981             87.651868
+    22  3072.0  81.825298  ...  88.612060             88.473602
-    23  3200.0  84.099871  ...  93.567248             94.674553
+    23  3200.0  84.880639  ...  95.096582             95.096582
-    24  3328.0  79.901550  ...  84.945483             84.496824
+    24  3328.0  83.808259  ...  84.101981             83.905938
-    25  3456.0  81.600781  ...  91.511426             84.775569
+    25  3456.0  78.655188  ...  85.950501             88.400840
-    26  3584.0  83.798127  ...  86.542919             95.148565
+    26  3584.0  87.296493  ...  97.628001             98.268190
-    27  3712.0  81.615477  ...  88.640059             82.017526
+    27  3712.0  80.757757  ...  88.326564             85.822459
-    28  3840.0  84.744825  ...  91.777595             85.399230
+    28  3840.0  83.027026  ...  91.059692             84.613126
-    29  3968.0  92.024087  ...  84.183469             89.558851
+    29  3968.0  90.724116  ...  87.347124             90.791620
-    30  4096.0  86.424811  ...  87.438257             91.992956
+    30  4096.0  86.313653  ...  86.424811             91.056800
 
     [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  4.559 seconds)
+   **Total running time of the script:** ( 5 minutes  56.072 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  0.480 seconds)
+   **Total running time of the script:** ( 0 minutes  0.482 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  307.200008   98.303995  307.200008
+    0    1024.0  307.200008   99.902435  307.200008
-    1    1536.0  347.773587  134.050910  341.333333
+    1    1536.0  351.085717  135.032961  341.333333
-    2    2048.0  420.102553  161.684218  325.509933
+    2    2048.0  420.102553  162.754967  327.679984
-    3    2560.0  458.507457  181.238943  326.808501
+    3    2560.0  458.507457  182.857144  330.322572
-    4    3072.0  511.999982  191.999993  317.793096
+    4    3072.0  515.580429  191.501303  319.168834
-    5    3584.0  547.872604  208.271186  310.527060
+    5    3584.0  547.872604  207.768111  311.652167
-    6    4096.0  564.965515  220.412561  294.323343
+    6    4096.0  568.231237  221.905193  301.546004
-    7    4608.0  504.986315  232.825259  290.267724
+    7    4608.0  504.986315  232.336141  287.999990
-    8    5120.0  527.381977  242.845844  287.775181
+    8    5120.0  531.948056  242.366855  285.104413
-    9    5632.0  542.843364  243.545956  288.820505
+    9    5632.0  538.517949  243.545956  290.683877
-    10   6144.0  546.133354  248.661056  285.767458
+    10   6144.0  546.133354  250.349744  288.000001
-    11   6656.0  532.479975  256.000009  285.767438
+    11   6656.0  536.053693  256.000009  286.279570
-    12   7168.0  507.469040  260.260201  286.242939
+    12   7168.0  510.480705  252.988236  277.024148
-    13   7680.0  479.999983  262.564106  279.272719
+    13   7680.0  482.513091  267.130429  284.444450
-    14   8192.0  462.607053  267.130429  284.526763
+    14   8192.0  463.698115  269.326017  282.482757
-    15   8704.0  417.791980  267.815384  284.599455
+    15   8704.0  417.791980  264.425310  282.673891
-    16   9216.0  431.157889  272.394084  288.751954
+    16   9216.0  431.157889  274.762727  291.031570
-    17   9728.0  438.857162  280.278512  290.027323
+    17   9728.0  439.683593  281.630872  290.027323
-    18  10240.0  449.287041  286.433562  290.153487
+    18  10240.0  446.025405  286.100109  289.811322
-    19  10752.0  427.231788  246.935876  290.594591
+    19  10752.0  425.120247  246.935876  289.941565
-    20  11264.0  426.397479  245.760001  286.676558
+    20  11264.0  425.056596  243.765566  283.371073
-    21  11776.0  423.089806  249.888595  288.981596
+    21  11776.0  423.089806  249.888595  289.129414
-    22  12288.0  419.504980  254.673582  294.323369
+    22  12288.0  421.302872  254.673582  295.207195
-    23  12800.0  414.016170  253.674644  288.180121
+    23  12800.0  414.574901  254.515329  290.909089
-    24  13312.0  411.181478  252.959629  289.916513
+    24  13312.0  414.381327  253.561895  289.129403
-    25  13824.0  404.112047  257.190689  292.056329
+    25  13824.0  406.090579  257.790206  293.088338
-    26  14336.0  393.215988  254.485198  286.719986
+    26  14336.0  394.116833  256.381525  290.349381
-    27  14848.0  385.245405  257.665934  289.012175
+    27  14848.0  385.245405  255.999999  287.844912
-    28  15360.0  373.495460  257.970599  286.211174
+    28  15360.0  376.932517  262.751252  291.184839
-    29  15872.0  371.637071  261.626369  289.899545
+    29  15872.0  370.913333  262.166551  291.118085
 
 
 
@@ -339,7 +339,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  12.003 seconds)
+   **Total running time of the script:** ( 2 minutes  11.560 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
 =================
-**13:21.645** total execution time for **getting-started_tutorials** files:
+**13:04.956** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:04.559 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:56.072 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:22.066 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:20.551 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.003 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:11.560 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:42.537 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:36.291 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.480 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.482 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -325,10 +325,10 @@ for different problem sizes.</p>
 0        4096.0    9.600000    9.600000
 1        8192.0   19.200000   19.200000
 2       16384.0   38.400001   38.400001
-3       32768.0   63.999998   63.999998
+3       32768.0   76.800002   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
@@ -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  42.537 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  36.291 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   190.511628
+0     256.0  546.133347      546.133347   190.511628
-1     384.0  614.400016      585.142862   153.600004
+1     384.0  585.142862      585.142862   153.600004
-2     512.0  655.360017      606.814814   154.566038
+2     512.0  655.360017      585.142849   156.038096
-3     640.0  706.206879      640.000002   160.000000
+3     640.0  682.666684      640.000002   160.000000
-4     768.0  722.823517      664.216187   162.754967
+4     768.0  722.823517      664.216187   163.839992
 ..      ...         ...             ...          ...
-93  12160.0  814.058574      406.179533   198.733401
+93  12160.0  814.058574      405.755985   198.936606
 94  12288.0  814.111783      415.661740   198.995960
-95  12416.0  814.163950      412.149375   198.556711
+95  12416.0  814.163950      411.722274   198.755369
-96  12544.0  814.214963      412.971190   198.815254
+96  12544.0  814.214963      412.971190   198.913776
-97  12672.0  814.265046      412.097543   198.873965
+97  12672.0  814.265046      412.516771   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  22.066 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  20.551 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  ...   2.978909              2.978909
+0    256.0   2.978909  ...   2.978909              3.276800
-1    384.0   7.372800  ...   8.507077              7.899428
+1    384.0   7.372800  ...   8.507077              8.507077
 2    512.0  14.563555  ...  16.384000             16.384000
 3    640.0  22.260869  ...  24.380953             24.380953
 4    768.0  32.768000  ...  34.028308             34.028308
-5    896.0  39.025776  ...  39.025776             39.025776
+5    896.0  37.971025  ...  40.140799             39.025776
 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
+10  1536.0  80.430545  ...  79.526831             79.526831
 11  1664.0  62.929456  ...  62.492442             62.061463
-12  1792.0  72.512412  ...  71.588687             72.047592
+12  1792.0  72.512412  ...  72.047592             72.047592
-13  1920.0  69.467336  ...  70.172588             70.172588
+13  1920.0  69.120002  ...  70.172588             70.530615
-14  2048.0  73.262953  ...  76.608294             76.608294
+14  2048.0  73.584279  ...  76.959706             76.608294
-15  2176.0  83.500614  ...  85.998493             85.998493
+15  2176.0  83.155572  ...  86.367588             85.269692
-16  2304.0  68.446623  ...  76.563695             76.319081
+16  2304.0  68.446623  ...  77.057651             76.076024
-17  2432.0  71.305746  ...  74.521127             85.134737
+17  2432.0  71.305746  ...  84.367759             85.134737
-18  2560.0  78.019048  ...  80.908642             81.108913
+18  2560.0  78.019048  ...  80.908642             80.709358
-19  2688.0  82.823267  ...  89.888756             89.464755
+19  2688.0  83.369354  ...  89.676257             89.254248
-20  2816.0  83.233226  ...  82.916747             82.759409
+20  2816.0  79.733474  ...  83.392363             83.233226
-21  2944.0  81.967162  ...  82.509987             82.237674
+21  2944.0  81.967162  ...  82.237674             82.102191
-22  3072.0  82.181572  ...  88.197981             87.651868
+22  3072.0  81.825298  ...  88.612060             88.473602
-23  3200.0  84.099871  ...  93.567248             94.674553
+23  3200.0  84.880639  ...  95.096582             95.096582
-24  3328.0  79.901550  ...  84.945483             84.496824
+24  3328.0  83.808259  ...  84.101981             83.905938
-25  3456.0  81.600781  ...  91.511426             84.775569
+25  3456.0  78.655188  ...  85.950501             88.400840
-26  3584.0  83.798127  ...  86.542919             95.148565
+26  3584.0  87.296493  ...  97.628001             98.268190
-27  3712.0  81.615477  ...  88.640059             82.017526
+27  3712.0  80.757757  ...  88.326564             85.822459
-28  3840.0  84.744825  ...  91.777595             85.399230
+28  3840.0  83.027026  ...  91.059692             84.613126
-29  3968.0  92.024087  ...  84.183469             89.558851
+29  3968.0  90.724116  ...  87.347124             90.791620
-30  4096.0  86.424811  ...  87.438257             91.992956
+30  4096.0  86.313653  ...  86.424811             91.056800
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  4.559 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  56.072 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  0.480 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.482 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  307.200008   98.303995  307.200008
+0    1024.0  307.200008   99.902435  307.200008
-1    1536.0  347.773587  134.050910  341.333333
+1    1536.0  351.085717  135.032961  341.333333
-2    2048.0  420.102553  161.684218  325.509933
+2    2048.0  420.102553  162.754967  327.679984
-3    2560.0  458.507457  181.238943  326.808501
+3    2560.0  458.507457  182.857144  330.322572
-4    3072.0  511.999982  191.999993  317.793096
+4    3072.0  515.580429  191.501303  319.168834
-5    3584.0  547.872604  208.271186  310.527060
+5    3584.0  547.872604  207.768111  311.652167
-6    4096.0  564.965515  220.412561  294.323343
+6    4096.0  568.231237  221.905193  301.546004
-7    4608.0  504.986315  232.825259  290.267724
+7    4608.0  504.986315  232.336141  287.999990
-8    5120.0  527.381977  242.845844  287.775181
+8    5120.0  531.948056  242.366855  285.104413
-9    5632.0  542.843364  243.545956  288.820505
+9    5632.0  538.517949  243.545956  290.683877
-10   6144.0  546.133354  248.661056  285.767458
+10   6144.0  546.133354  250.349744  288.000001
-11   6656.0  532.479975  256.000009  285.767438
+11   6656.0  536.053693  256.000009  286.279570
-12   7168.0  507.469040  260.260201  286.242939
+12   7168.0  510.480705  252.988236  277.024148
-13   7680.0  479.999983  262.564106  279.272719
+13   7680.0  482.513091  267.130429  284.444450
-14   8192.0  462.607053  267.130429  284.526763
+14   8192.0  463.698115  269.326017  282.482757
-15   8704.0  417.791980  267.815384  284.599455
+15   8704.0  417.791980  264.425310  282.673891
-16   9216.0  431.157889  272.394084  288.751954
+16   9216.0  431.157889  274.762727  291.031570
-17   9728.0  438.857162  280.278512  290.027323
+17   9728.0  439.683593  281.630872  290.027323
-18  10240.0  449.287041  286.433562  290.153487
+18  10240.0  446.025405  286.100109  289.811322
-19  10752.0  427.231788  246.935876  290.594591
+19  10752.0  425.120247  246.935876  289.941565
-20  11264.0  426.397479  245.760001  286.676558
+20  11264.0  425.056596  243.765566  283.371073
-21  11776.0  423.089806  249.888595  288.981596
+21  11776.0  423.089806  249.888595  289.129414
-22  12288.0  419.504980  254.673582  294.323369
+22  12288.0  421.302872  254.673582  295.207195
-23  12800.0  414.016170  253.674644  288.180121
+23  12800.0  414.574901  254.515329  290.909089
-24  13312.0  411.181478  252.959629  289.916513
+24  13312.0  414.381327  253.561895  289.129403
-25  13824.0  404.112047  257.190689  292.056329
+25  13824.0  406.090579  257.790206  293.088338
-26  14336.0  393.215988  254.485198  286.719986
+26  14336.0  394.116833  256.381525  290.349381
-27  14848.0  385.245405  257.665934  289.012175
+27  14848.0  385.245405  255.999999  287.844912
-28  15360.0  373.495460  257.970599  286.211174
+28  15360.0  376.932517  262.751252  291.184839
-29  15872.0  371.637071  261.626369  289.899545
+29  15872.0  370.913333  262.166551  291.118085
 </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  12.003 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  11.560 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>13:21.645</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:04.956</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>06:04.559</p></td>
+<td><p>05:56.072</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>03:22.066</p></td>
+<td><p>03:20.551</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>02:12.003</p></td>
+<td><p>02:11.560</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>01:42.537</p></td>
+<td><p>01:36.291</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>00:00.480</p></td>
+<td><p>00:00.482</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: 10000303ff39f4e8f843aab886b6f63e
+config: 68db870c73f557363c04552ac96820c6
 tags: 645f666f9bcd5a90fca523b33c5a78b7