[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: 5d1e5336b0fe1254665c1a22d9c46408
+config: e596642ff1cf86c1376bbeb43852c411
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -235,13 +235,13 @@ 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  341.333321  384.000001
     7      524288.0  472.615390  472.615390
     8     1048576.0  614.400016  614.400016
-    9     2097152.0  722.823517  702.171410
+    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
@@ -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  24.953 seconds)
+   **Total running time of the script:** ( 1 minutes  38.189 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   190.511628
-    1     384.0  585.142862      558.545450   151.703707
+    0     256.0  546.133347      546.133347   188.321838
+    1     384.0  585.142862      585.142862   151.703707
     2     512.0  655.360017      606.814814   154.566038
     3     640.0  682.666684      640.000002   158.759699
     4     768.0  722.823517      664.216187   163.839992
     ..      ...         ...             ...          ...
-    93  12160.0  814.058574      405.755985   198.530610
-    94  12288.0  814.111783      415.222812   198.794749
+    93  12160.0  814.058574      405.755985   198.631953
+    94  12288.0  814.111783      415.661740   198.794749
     95  12416.0  814.163950      412.149375   198.457532
-    96  12544.0  814.214963      412.971190   198.618504
+    96  12544.0  814.214963      412.971190   198.716830
     97  12672.0  814.265046      411.679167   198.776477
 
     [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  19.032 seconds)
+   **Total running time of the script:** ( 3 minutes  22.664 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -457,38 +457,38 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
  .. code-block:: none
 
     matmul-performance:
-             M     cuBLAS  ...      Triton  Triton (+ LeakyReLU)
-    0    256.0   2.730667  ...    2.978909              3.276800
-    1    384.0   7.372800  ...    7.899428              7.899428
-    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
-    5    896.0  37.971025  ...   40.140799             40.140799
-    6   1024.0  49.932191  ...   53.773130             53.773130
-    7   1152.0  45.242181  ...   48.161033             47.396572
-    8   1280.0  51.200001  ...   57.690139             57.690139
-    9   1408.0  64.138541  ...   69.009825             68.147202
-    10  1536.0  80.430545  ...   80.430545             80.430545
-    11  1664.0  62.929456  ...   63.372618             62.929456
-    12  1792.0  72.983276  ...   63.499573             63.142831
-    13  1920.0  68.776119  ...   71.257735             71.257735
-    14  2048.0  73.584279  ...   78.398206             78.033565
-    15  2176.0  83.500614  ...   87.115360             86.739860
-    16  2304.0  68.251065  ...   78.320893             77.810656
-    17  2432.0  71.305746  ...   75.726318             75.522751
-    18  2560.0  77.833728  ...   82.331658             81.715711
-    19  2688.0  83.552988  ...   90.966561             90.966561
-    20  2816.0  82.602666  ...   84.687779             84.523664
-    21  2944.0  82.921853  ...   83.758038             84.182483
-    22  3072.0  82.181572  ...   89.170242             88.197981
-    23  3200.0  81.321474  ...   95.238096             94.395283
-    24  3328.0  82.939284  ...   86.320498             85.908470
-    25  3456.0  80.140726  ...   87.727494             91.407671
-    26  3584.0  87.381330  ...  100.128496             99.684470
-    27  3712.0  83.247783  ...   87.629253             89.194055
-    28  3840.0  84.228485  ...   92.236860             85.533390
-    29  3968.0  91.885495  ...   85.093402             90.589410
-    30  4096.0  91.616198  ...   93.792965             91.242506
+             M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
+    0    256.0   2.978909  ...   3.276800              2.978909
+    1    384.0   7.372800  ...   7.899428              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  ...  35.389441             34.028308
+    5    896.0  37.971025  ...  40.140799             39.025776
+    6   1024.0  49.932191  ...  53.773130             52.428801
+    7   1152.0  45.242181  ...  48.161033             47.396572
+    8   1280.0  51.200001  ...  57.690139             57.690139
+    9   1408.0  64.138541  ...  68.147202             67.305878
+    10  1536.0  79.526831  ...  79.526831             79.526831
+    11  1664.0  62.929456  ...  63.372618             62.929456
+    12  1792.0  72.512412  ...  63.142831             62.790080
+    13  1920.0  69.120002  ...  71.257735             70.892307
+    14  2048.0  73.262953  ...  78.033565             77.672296
+    15  2176.0  83.155572  ...  87.115360             86.739860
+    16  2304.0  68.251065  ...  77.810656             77.810656
+    17  2432.0  71.305746  ...  75.522751             75.320281
+    18  2560.0  77.833728  ...  82.539044             82.125311
+    19  2688.0  83.737433  ...  91.185232             90.748936
+    20  2816.0  84.523664  ...  81.445766             84.523664
+    21  2944.0  81.298583  ...  83.899046             84.040530
+    22  3072.0  82.540970  ...  90.164177             89.735509
+    23  3200.0  84.656085  ...  96.385543             96.240602
+    24  3328.0  83.226931  ...  85.602017             84.249616
+    25  3456.0  81.849303  ...  85.133652             84.864807
+    26  3584.0  87.466332  ...  99.684470             99.354022
+    27  3712.0  81.548851  ...  84.159518             87.706180
+    28  3840.0  84.874902  ...  86.535214             91.398346
+    29  3968.0  88.040360  ...  92.442373             86.480463
+    30  4096.0  93.760204  ...  91.992956             90.871857
 
     [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:** ( 5 minutes  44.529 seconds)
+   **Total running time of the script:** ( 6 minutes  30.096 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  0.013 seconds)
+   **Total running time of the script:** ( 0 minutes  0.324 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

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

@@ -40,34 +40,34 @@ Layer Normalization
               N      Triton       Torch        Apex
     0    1024.0  361.411758   97.912354  303.407414
     1    1536.0  409.599994  134.540150  341.333333
-    2    2048.0  491.520012  161.154101  334.367350
-    3    2560.0  461.954908  181.238943  330.322572
-    4    3072.0  519.211251  192.501302  323.368415
-    5    3584.0  558.545477  208.271186  311.652167
-    6    4096.0  568.231237  220.907859  298.796351
-    7    4608.0  502.690905  232.825259  287.251954
-    8    5120.0  527.381977  242.366855  284.444444
-    9    5632.0  542.843364  243.107920  289.438969
+    2    2048.0  491.520012  161.154101  323.368435
+    3    2560.0  461.954908  181.238943  326.808501
+    4    3072.0  515.580429  192.501302  320.556515
+    5    3584.0  554.941930  208.271186  311.652167
+    6    4096.0  561.737163  220.907859  294.323343
+    7    4608.0  502.690905  232.825259  291.799469
+    8    5120.0  525.128191  242.366855  289.129408
+    9    5632.0  540.671974  243.107920  288.820505
     10   6144.0  546.133354  248.661056  286.322318
-    11   6656.0  527.207907  256.000009  285.767438
-    12   7168.0  503.017523  259.867079  284.821192
-    13   7680.0  483.779539  262.938666  280.121579
-    14   8192.0  463.698115  266.587109  284.526763
-    15   8704.0  414.476194  267.815384  284.599455
-    16   9216.0  426.996150  271.391419  287.999990
-    17   9728.0  437.213490  280.278512  290.027323
-    18  10240.0  446.025405  286.433562  290.496460
-    19  10752.0  429.364408  247.172406  290.594591
-    20  11264.0  427.071098  245.313973  286.980888
-    21  11776.0  421.198220  249.667843  289.277383
-    22  12288.0  416.542386  254.893699  294.617366
-    23  12800.0  411.244989  253.884294  289.811310
+    11   6656.0  527.207907  256.000009  285.257135
+    12   7168.0  503.017523  260.063480  285.293536
+    13   7680.0  483.779539  262.938666  275.928134
+    14   8192.0  463.698115  266.767970  284.526763
+    15   8704.0  413.655443  267.472468  284.987724
+    16   9216.0  427.822068  271.724806  288.375482
+    17   9728.0  436.396262  280.615388  289.667485
+    18  10240.0  446.025405  286.433562  290.153487
+    19  10752.0  428.651173  246.935876  290.267711
+    20  11264.0  426.397479  245.536784  286.980888
+    21  11776.0  420.571432  249.667843  288.981596
+    22  12288.0  416.542386  254.673582  294.617366
+    23  12800.0  410.695192  253.884294  288.180121
     24  13312.0  409.075539  252.959629  290.443638
-    25  13824.0  405.098897  257.390218  292.056329
-    26  14336.0  395.021816  254.862216  287.198654
-    27  14848.0  386.498925  257.852379  289.717061
-    28  15360.0  380.433442  257.970599  287.550706
-    29  15872.0  370.552519  261.626369  290.120338
+    25  13824.0  404.604870  257.390218  292.056329
+    26  14336.0  394.116833  254.862216  286.959121
+    27  14848.0  385.662341  257.852379  289.952797
+    28  15360.0  380.433442  257.970599  286.433562
+    29  15872.0  370.192407  261.626369  290.562936
 
 
 
@@ -339,7 +339,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  12.505 seconds)
+   **Total running time of the script:** ( 2 minutes  14.541 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
 =================
-**12:41.032** total execution time for **getting-started_tutorials** files:
+**13:45.813** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:44.529 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:30.096 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:19.032 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:22.664 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.505 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:14.541 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:24.953 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:38.189 | 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 |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.324 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -325,13 +325,13 @@ 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  341.333321  384.000001
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
-9     2097152.0  722.823517  702.171410
+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
@@ -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  24.953 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  38.189 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   190.511628
-1     384.0  585.142862      558.545450   151.703707
+0     256.0  546.133347      546.133347   188.321838
+1     384.0  585.142862      585.142862   151.703707
 2     512.0  655.360017      606.814814   154.566038
 3     640.0  682.666684      640.000002   158.759699
 4     768.0  722.823517      664.216187   163.839992
 ..      ...         ...             ...          ...
-93  12160.0  814.058574      405.755985   198.530610
-94  12288.0  814.111783      415.222812   198.794749
+93  12160.0  814.058574      405.755985   198.631953
+94  12288.0  814.111783      415.661740   198.794749
 95  12416.0  814.163950      412.149375   198.457532
-96  12544.0  814.214963      412.971190   198.618504
+96  12544.0  814.214963      412.971190   198.716830
 97  12672.0  814.265046      411.679167   198.776477
 
 [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  19.032 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  22.664 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

@@ -563,43 +563,43 @@ torch_output=tensor([[  1.1045, -36.9688,  31.4688,  ..., -11.3906,  24.4531, -3
 <img alt="03 matrix multiplication" class="sphx-glr-single-img" src="../../_images/sphx_glr_03-matrix-multiplication_001.png" />
 <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              3.276800
-1    384.0   7.372800  ...    7.899428              7.899428
-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
-5    896.0  37.971025  ...   40.140799             40.140799
-6   1024.0  49.932191  ...   53.773130             53.773130
-7   1152.0  45.242181  ...   48.161033             47.396572
-8   1280.0  51.200001  ...   57.690139             57.690139
-9   1408.0  64.138541  ...   69.009825             68.147202
-10  1536.0  80.430545  ...   80.430545             80.430545
-11  1664.0  62.929456  ...   63.372618             62.929456
-12  1792.0  72.983276  ...   63.499573             63.142831
-13  1920.0  68.776119  ...   71.257735             71.257735
-14  2048.0  73.584279  ...   78.398206             78.033565
-15  2176.0  83.500614  ...   87.115360             86.739860
-16  2304.0  68.251065  ...   78.320893             77.810656
-17  2432.0  71.305746  ...   75.726318             75.522751
-18  2560.0  77.833728  ...   82.331658             81.715711
-19  2688.0  83.552988  ...   90.966561             90.966561
-20  2816.0  82.602666  ...   84.687779             84.523664
-21  2944.0  82.921853  ...   83.758038             84.182483
-22  3072.0  82.181572  ...   89.170242             88.197981
-23  3200.0  81.321474  ...   95.238096             94.395283
-24  3328.0  82.939284  ...   86.320498             85.908470
-25  3456.0  80.140726  ...   87.727494             91.407671
-26  3584.0  87.381330  ...  100.128496             99.684470
-27  3712.0  83.247783  ...   87.629253             89.194055
-28  3840.0  84.228485  ...   92.236860             85.533390
-29  3968.0  91.885495  ...   85.093402             90.589410
-30  4096.0  91.616198  ...   93.792965             91.242506
+         M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
+0    256.0   2.978909  ...   3.276800              2.978909
+1    384.0   7.372800  ...   7.899428              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  ...  35.389441             34.028308
+5    896.0  37.971025  ...  40.140799             39.025776
+6   1024.0  49.932191  ...  53.773130             52.428801
+7   1152.0  45.242181  ...  48.161033             47.396572
+8   1280.0  51.200001  ...  57.690139             57.690139
+9   1408.0  64.138541  ...  68.147202             67.305878
+10  1536.0  79.526831  ...  79.526831             79.526831
+11  1664.0  62.929456  ...  63.372618             62.929456
+12  1792.0  72.512412  ...  63.142831             62.790080
+13  1920.0  69.120002  ...  71.257735             70.892307
+14  2048.0  73.262953  ...  78.033565             77.672296
+15  2176.0  83.155572  ...  87.115360             86.739860
+16  2304.0  68.251065  ...  77.810656             77.810656
+17  2432.0  71.305746  ...  75.522751             75.320281
+18  2560.0  77.833728  ...  82.539044             82.125311
+19  2688.0  83.737433  ...  91.185232             90.748936
+20  2816.0  84.523664  ...  81.445766             84.523664
+21  2944.0  81.298583  ...  83.899046             84.040530
+22  3072.0  82.540970  ...  90.164177             89.735509
+23  3200.0  84.656085  ...  96.385543             96.240602
+24  3328.0  83.226931  ...  85.602017             84.249616
+25  3456.0  81.849303  ...  85.133652             84.864807
+26  3584.0  87.466332  ...  99.684470             99.354022
+27  3712.0  81.548851  ...  84.159518             87.706180
+28  3840.0  84.874902  ...  86.535214             91.398346
+29  3968.0  88.040360  ...  92.442373             86.480463
+30  4096.0  93.760204  ...  91.992956             90.871857
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  44.529 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  30.096 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  0.013 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.324 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

@@ -196,34 +196,34 @@ to download the full example code</p>
           N      Triton       Torch        Apex
 0    1024.0  361.411758   97.912354  303.407414
 1    1536.0  409.599994  134.540150  341.333333
-2    2048.0  491.520012  161.154101  334.367350
-3    2560.0  461.954908  181.238943  330.322572
-4    3072.0  519.211251  192.501302  323.368415
-5    3584.0  558.545477  208.271186  311.652167
-6    4096.0  568.231237  220.907859  298.796351
-7    4608.0  502.690905  232.825259  287.251954
-8    5120.0  527.381977  242.366855  284.444444
-9    5632.0  542.843364  243.107920  289.438969
+2    2048.0  491.520012  161.154101  323.368435
+3    2560.0  461.954908  181.238943  326.808501
+4    3072.0  515.580429  192.501302  320.556515
+5    3584.0  554.941930  208.271186  311.652167
+6    4096.0  561.737163  220.907859  294.323343
+7    4608.0  502.690905  232.825259  291.799469
+8    5120.0  525.128191  242.366855  289.129408
+9    5632.0  540.671974  243.107920  288.820505
 10   6144.0  546.133354  248.661056  286.322318
-11   6656.0  527.207907  256.000009  285.767438
-12   7168.0  503.017523  259.867079  284.821192
-13   7680.0  483.779539  262.938666  280.121579
-14   8192.0  463.698115  266.587109  284.526763
-15   8704.0  414.476194  267.815384  284.599455
-16   9216.0  426.996150  271.391419  287.999990
-17   9728.0  437.213490  280.278512  290.027323
-18  10240.0  446.025405  286.433562  290.496460
-19  10752.0  429.364408  247.172406  290.594591
-20  11264.0  427.071098  245.313973  286.980888
-21  11776.0  421.198220  249.667843  289.277383
-22  12288.0  416.542386  254.893699  294.617366
-23  12800.0  411.244989  253.884294  289.811310
+11   6656.0  527.207907  256.000009  285.257135
+12   7168.0  503.017523  260.063480  285.293536
+13   7680.0  483.779539  262.938666  275.928134
+14   8192.0  463.698115  266.767970  284.526763
+15   8704.0  413.655443  267.472468  284.987724
+16   9216.0  427.822068  271.724806  288.375482
+17   9728.0  436.396262  280.615388  289.667485
+18  10240.0  446.025405  286.433562  290.153487
+19  10752.0  428.651173  246.935876  290.267711
+20  11264.0  426.397479  245.536784  286.980888
+21  11776.0  420.571432  249.667843  288.981596
+22  12288.0  416.542386  254.673582  294.617366
+23  12800.0  410.695192  253.884294  288.180121
 24  13312.0  409.075539  252.959629  290.443638
-25  13824.0  405.098897  257.390218  292.056329
-26  14336.0  395.021816  254.862216  287.198654
-27  14848.0  386.498925  257.852379  289.717061
-28  15360.0  380.433442  257.970599  287.550706
-29  15872.0  370.552519  261.626369  290.120338
+25  13824.0  404.604870  257.390218  292.056329
+26  14336.0  394.116833  254.862216  286.959121
+27  14848.0  385.662341  257.852379  289.952797
+28  15360.0  380.433442  257.970599  286.433562
+29  15872.0  370.192407  261.626369  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  12.505 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  14.541 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>12:41.032</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:45.813</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>05:44.529</p></td>
+<td><p>06:30.096</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>03:19.032</p></td>
+<td><p>03:22.664</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>02:12.505</p></td>
+<td><p>02:14.541</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>01:24.953</p></td>
+<td><p>01:38.189</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>00:00.013</p></td>
+<td><p>00:00.324</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: a6cd588efd8cbca3a53386f847952a2b
+config: bcbfc296459f44b018098bb64725701b
 tags: 645f666f9bcd5a90fca523b33c5a78b7