[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: b8d6e434bf0cea6b075c4f17e1d5f683
+config: 129fe056d957bceb5eb7005a87aa6582
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -232,20 +232,20 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
 
     vector-add-performance:
                size      Triton       Torch
-    0        4096.0    9.600000    9.600000
+    0        4096.0    8.000000    9.600000
     1        8192.0   19.200000   19.200000
     2       16384.0   38.400001   38.400001
     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  341.333321
+    6      262144.0  341.333321  384.000001
     7      524288.0  472.615390  472.615390
     8     1048576.0  614.400016  614.400016
-    9     2097152.0  722.823517  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
-    13   33554432.0  842.004273  843.811163
+    13   33554432.0  842.004273  842.004273
     14   67108864.0  847.448255  848.362445
     15  134217728.0  849.737435  850.656574
 
@@ -255,7 +255,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  47.140 seconds)
+   **Total running time of the script:** ( 1 minutes  46.935 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  546.133347      512.000001   186.181817
+    0     256.0  512.000001      546.133347   188.321838
-    1     384.0  585.142862      585.142862   151.703707
+    1     384.0  585.142862      558.545450   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   162.754967
+    4     768.0  722.823517      664.216187   163.839992
     ..      ...         ...             ...          ...
-    93  12160.0  814.058574      405.755985   198.936606
+    93  12160.0  814.058574      405.755985   198.733401
     94  12288.0  814.111783      415.661740   198.995960
-    95  12416.0  814.163950      411.296057   198.805107
+    95  12416.0  814.163950      411.722274   198.705656
-    96  12544.0  814.214963      412.971190   198.913776
+    96  12544.0  814.214963      412.971190   198.815254
-    97  12672.0  814.265046      411.888249   198.971549
+    97  12672.0  814.265046      411.679167   198.971549
 
     [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  27.130 seconds)
+   **Total running time of the script:** ( 3 minutes  27.513 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  ...   8.507077              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             15.420235
     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
+    5    896.0  37.971025  ...  40.140799             39.025776
-    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
     8   1280.0  51.200001  ...  57.690139             57.690139
-    9   1408.0  64.138541  ...  68.147202             68.147202
+    9   1408.0  64.138541  ...  69.009825             68.147202
-    10  1536.0  80.430545  ...  81.355034             79.526831
+    10  1536.0  80.430545  ...  80.430545             80.430545
-    11  1664.0  62.929456  ...  63.372618             62.929456
+    11  1664.0  63.372618  ...  63.372618             63.372618
     12  1792.0  72.983276  ...  63.499573             63.142831
-    13  1920.0  68.776119  ...  71.257735             71.257735
+    13  1920.0  69.120002  ...  71.626943             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  ...  78.064941             77.810656
+    16  2304.0  68.251065  ...  78.064941             77.558029
     17  2432.0  71.305746  ...  75.726318             75.522751
-    18  2560.0  77.833728  ...  82.125311             81.715711
+    18  2560.0  77.833728  ...  82.125311             82.125311
-    19  2688.0  83.369354  ...  90.748936             90.748936
+    19  2688.0  83.552988  ...  90.316801             90.966561
-    20  2816.0  82.290955  ...  84.523664             84.360174
+    20  2816.0  83.233226  ...  83.233226             84.278666
-    21  2944.0  82.373605  ...  83.617504             82.373605
+    21  2944.0  81.166173  ...  83.617504             84.182483
-    22  3072.0  82.062468  ...  89.735509             88.473602
+    22  3072.0  81.825298  ...  89.451983             89.451983
-    23  3200.0  80.503145  ...  94.674553             95.380032
+    23  3200.0  83.989503  ...  96.530922             94.256261
-    24  3328.0  82.369902  ...  86.320498             86.736504
+    24  3328.0  83.905938  ...  86.946008             86.217120
-    25  3456.0  78.578525  ...  84.332184             87.823058
+    25  3456.0  80.300370  ...  92.350019             88.497878
-    26  3584.0  87.381330  ...  99.684470             99.463928
+    26  3584.0  87.381330  ...  98.053863             99.463928
-    27  3712.0  83.247783  ...  89.916604             87.018592
+    27  3712.0  85.528545  ...  87.629253             88.326564
-    28  3840.0  84.874902  ...  92.275341             86.332554
+    28  3840.0  82.716526  ...  88.971840             91.625518
-    29  3968.0  92.864488  ...  86.664727             92.512459
+    29  3968.0  87.004591  ...  92.652949             85.841672
-    30  4096.0  86.592080  ...  87.552332             93.271527
+    30  4096.0  93.727466  ...  89.092421             87.495257
 
     [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  16.209 seconds)
+   **Total running time of the script:** ( 6 minutes  7.255 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  0.014 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   99.497980  311.088617
+    0    1024.0  361.411758   97.912354  303.407414
-    1    1536.0  405.098894  133.083026  344.523365
+    1    1536.0  405.098894  134.540150  341.333333
-    2    2048.0  496.484863  158.045011  334.367350
+    2    2048.0  491.520012  161.154101  334.367350
-    3    2560.0  461.954908  182.857144  330.322572
+    3    2560.0  465.454542  181.238943  330.322572
-    4    3072.0  519.211251  191.501303  320.556515
+    4    3072.0  519.211251  192.501302  323.368415
-    5    3584.0  554.941930  208.271186  308.301075
+    5    3584.0  558.545477  208.271186  311.652167
-    6    4096.0  564.965515  220.412561  298.796351
+    6    4096.0  564.965515  220.907859  298.796351
-    7    4608.0  500.416301  232.336141  286.507772
+    7    4608.0  502.690905  232.825259  287.251954
-    8    5120.0  529.655159  243.809526  286.433562
+    8    5120.0  527.381977  242.366855  284.444444
-    9    5632.0  542.843364  244.426754  291.310338
+    9    5632.0  542.843364  243.107920  289.438969
-    10   6144.0  548.163546  251.202731  286.879370
+    10   6144.0  546.133354  248.661056  286.322318
-    11   6656.0  534.260858  256.410903  286.793541
+    11   6656.0  527.207907  256.000009  285.767438
-    12   7168.0  513.528374  253.360829  277.470965
+    12   7168.0  503.017523  259.867079  284.821192
-    13   7680.0  486.332448  266.743841  284.884090
+    13   7680.0  482.513091  263.314295  280.121579
-    14   8192.0  468.114289  258.694729  277.694924
+    14   8192.0  463.698115  266.767970  284.526763
-    15   8704.0  414.476194  267.472468  286.158893
+    15   8704.0  414.476194  267.815384  284.599455
-    16   9216.0  428.651187  273.066667  289.507855
+    16   9216.0  427.822068  271.724806  287.999990
-    17   9728.0  438.857162  279.942444  288.593329
+    17   9728.0  437.213490  280.615388  290.027323
-    18  10240.0  445.217381  287.102804  290.153487
+    18  10240.0  446.836366  286.433562  290.496460
-    19  10752.0  427.231788  246.699797  289.941565
+    19  10752.0  429.364408  246.935876  290.267711
-    20  11264.0  427.071098  246.432094  288.204696
+    20  11264.0  426.397479  245.313973  286.980888
-    21  11776.0  421.826879  249.667843  289.573776
+    21  11776.0  420.571432  249.667843  288.981596
-    22  12288.0  417.131525  254.673582  294.323369
+    22  12288.0  416.542386  254.673582  294.323369
-    23  12800.0  411.244989  253.989249  290.084977
+    23  12800.0  411.244989  253.779426  289.811310
-    24  13312.0  409.599999  253.160074  289.391298
+    24  13312.0  409.075539  252.959629  290.443638
-    25  13824.0  405.842204  256.991469  292.313649
+    25  13824.0  405.098897  257.390218  292.056329
-    26  14336.0  395.475867  255.619613  288.402346
+    26  14336.0  395.021816  255.051144  286.719986
-    27  14848.0  383.999990  256.922861  288.544136
+    27  14848.0  386.080180  257.852379  289.481735
-    28  15360.0  380.041240  258.513318  288.225185
+    28  15360.0  380.433442  257.970599  286.879376
-    29  15872.0  372.000001  261.446802  289.239176
+    29  15872.0  371.094003  261.626369  289.679087
 
 
 
@@ -339,7 +339,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  13.538 seconds)
+   **Total running time of the script:** ( 2 minutes  14.074 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
 =================
-**13:44.030** total execution time for **getting-started_tutorials** files:
+**13:35.790** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:16.209 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:07.255 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:27.130 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:27.513 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:13.538 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:14.074 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:47.140 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:46.935 | 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``)       | 00:00.014 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -322,25 +322,25 @@ for different problem sizes.</p>
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector-add-performance:
            size      Triton       Torch
-0        4096.0    9.600000    9.600000
+0        4096.0    8.000000    9.600000
 1        8192.0   19.200000   19.200000
 2       16384.0   38.400001   38.400001
 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  341.333321
+6      262144.0  341.333321  384.000001
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
-9     2097152.0  722.823517  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
-13   33554432.0  842.004273  843.811163
+13   33554432.0  842.004273  842.004273
 14   67108864.0  847.448255  848.362445
 15  134217728.0  849.737435  850.656574
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  47.140 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  46.935 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  546.133347      512.000001   186.181817
+0     256.0  512.000001      546.133347   188.321838
-1     384.0  585.142862      585.142862   151.703707
+1     384.0  585.142862      558.545450   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   162.754967
+4     768.0  722.823517      664.216187   163.839992
 ..      ...         ...             ...          ...
-93  12160.0  814.058574      405.755985   198.936606
+93  12160.0  814.058574      405.755985   198.733401
 94  12288.0  814.111783      415.661740   198.995960
-95  12416.0  814.163950      411.296057   198.805107
+95  12416.0  814.163950      411.722274   198.705656
-96  12544.0  814.214963      412.971190   198.913776
+96  12544.0  814.214963      412.971190   198.815254
-97  12672.0  814.265046      411.888249   198.971549
+97  12672.0  814.265046      411.679167   198.971549
 
 [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  27.130 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  27.513 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  ...   8.507077              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             15.420235
 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
+5    896.0  37.971025  ...  40.140799             39.025776
-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
 8   1280.0  51.200001  ...  57.690139             57.690139
-9   1408.0  64.138541  ...  68.147202             68.147202
+9   1408.0  64.138541  ...  69.009825             68.147202
-10  1536.0  80.430545  ...  81.355034             79.526831
+10  1536.0  80.430545  ...  80.430545             80.430545
-11  1664.0  62.929456  ...  63.372618             62.929456
+11  1664.0  63.372618  ...  63.372618             63.372618
 12  1792.0  72.983276  ...  63.499573             63.142831
-13  1920.0  68.776119  ...  71.257735             71.257735
+13  1920.0  69.120002  ...  71.626943             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  ...  78.064941             77.810656
+16  2304.0  68.251065  ...  78.064941             77.558029
 17  2432.0  71.305746  ...  75.726318             75.522751
-18  2560.0  77.833728  ...  82.125311             81.715711
+18  2560.0  77.833728  ...  82.125311             82.125311
-19  2688.0  83.369354  ...  90.748936             90.748936
+19  2688.0  83.552988  ...  90.316801             90.966561
-20  2816.0  82.290955  ...  84.523664             84.360174
+20  2816.0  83.233226  ...  83.233226             84.278666
-21  2944.0  82.373605  ...  83.617504             82.373605
+21  2944.0  81.166173  ...  83.617504             84.182483
-22  3072.0  82.062468  ...  89.735509             88.473602
+22  3072.0  81.825298  ...  89.451983             89.451983
-23  3200.0  80.503145  ...  94.674553             95.380032
+23  3200.0  83.989503  ...  96.530922             94.256261
-24  3328.0  82.369902  ...  86.320498             86.736504
+24  3328.0  83.905938  ...  86.946008             86.217120
-25  3456.0  78.578525  ...  84.332184             87.823058
+25  3456.0  80.300370  ...  92.350019             88.497878
-26  3584.0  87.381330  ...  99.684470             99.463928
+26  3584.0  87.381330  ...  98.053863             99.463928
-27  3712.0  83.247783  ...  89.916604             87.018592
+27  3712.0  85.528545  ...  87.629253             88.326564
-28  3840.0  84.874902  ...  92.275341             86.332554
+28  3840.0  82.716526  ...  88.971840             91.625518
-29  3968.0  92.864488  ...  86.664727             92.512459
+29  3968.0  87.004591  ...  92.652949             85.841672
-30  4096.0  86.592080  ...  87.552332             93.271527
+30  4096.0  93.727466  ...  89.092421             87.495257
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  16.209 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  7.255 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  0.014 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   99.497980  311.088617
+0    1024.0  361.411758   97.912354  303.407414
-1    1536.0  405.098894  133.083026  344.523365
+1    1536.0  405.098894  134.540150  341.333333
-2    2048.0  496.484863  158.045011  334.367350
+2    2048.0  491.520012  161.154101  334.367350
-3    2560.0  461.954908  182.857144  330.322572
+3    2560.0  465.454542  181.238943  330.322572
-4    3072.0  519.211251  191.501303  320.556515
+4    3072.0  519.211251  192.501302  323.368415
-5    3584.0  554.941930  208.271186  308.301075
+5    3584.0  558.545477  208.271186  311.652167
-6    4096.0  564.965515  220.412561  298.796351
+6    4096.0  564.965515  220.907859  298.796351
-7    4608.0  500.416301  232.336141  286.507772
+7    4608.0  502.690905  232.825259  287.251954
-8    5120.0  529.655159  243.809526  286.433562
+8    5120.0  527.381977  242.366855  284.444444
-9    5632.0  542.843364  244.426754  291.310338
+9    5632.0  542.843364  243.107920  289.438969
-10   6144.0  548.163546  251.202731  286.879370
+10   6144.0  546.133354  248.661056  286.322318
-11   6656.0  534.260858  256.410903  286.793541
+11   6656.0  527.207907  256.000009  285.767438
-12   7168.0  513.528374  253.360829  277.470965
+12   7168.0  503.017523  259.867079  284.821192
-13   7680.0  486.332448  266.743841  284.884090
+13   7680.0  482.513091  263.314295  280.121579
-14   8192.0  468.114289  258.694729  277.694924
+14   8192.0  463.698115  266.767970  284.526763
-15   8704.0  414.476194  267.472468  286.158893
+15   8704.0  414.476194  267.815384  284.599455
-16   9216.0  428.651187  273.066667  289.507855
+16   9216.0  427.822068  271.724806  287.999990
-17   9728.0  438.857162  279.942444  288.593329
+17   9728.0  437.213490  280.615388  290.027323
-18  10240.0  445.217381  287.102804  290.153487
+18  10240.0  446.836366  286.433562  290.496460
-19  10752.0  427.231788  246.699797  289.941565
+19  10752.0  429.364408  246.935876  290.267711
-20  11264.0  427.071098  246.432094  288.204696
+20  11264.0  426.397479  245.313973  286.980888
-21  11776.0  421.826879  249.667843  289.573776
+21  11776.0  420.571432  249.667843  288.981596
-22  12288.0  417.131525  254.673582  294.323369
+22  12288.0  416.542386  254.673582  294.323369
-23  12800.0  411.244989  253.989249  290.084977
+23  12800.0  411.244989  253.779426  289.811310
-24  13312.0  409.599999  253.160074  289.391298
+24  13312.0  409.075539  252.959629  290.443638
-25  13824.0  405.842204  256.991469  292.313649
+25  13824.0  405.098897  257.390218  292.056329
-26  14336.0  395.475867  255.619613  288.402346
+26  14336.0  395.021816  255.051144  286.719986
-27  14848.0  383.999990  256.922861  288.544136
+27  14848.0  386.080180  257.852379  289.481735
-28  15360.0  380.041240  258.513318  288.225185
+28  15360.0  380.433442  257.970599  286.879376
-29  15872.0  372.000001  261.446802  289.239176
+29  15872.0  371.094003  261.626369  289.679087
 </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  13.538 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  14.074 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>13:44.030</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:35.790</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>06:16.209</p></td>
+<td><p>06:07.255</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>03:27.130</p></td>
+<td><p>03:27.513</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>02:13.538</p></td>
+<td><p>02:14.074</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>01:47.140</p></td>
+<td><p>01:46.935</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>00:00.014</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: cca517f91a1d454dce695daa3043ae9a
+config: aed21cdacbdf500daf084db5d1fa5e10
 tags: 645f666f9bcd5a90fca523b33c5a78b7