[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: bbf13b0f91abba000f682ef71c0ca565
+config: 1b584902668bd40609d4cad005c16910
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -235,7 +235,7 @@ 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
@@ -245,7 +245,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     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  46.048 seconds)
+   **Total running time of the script:** ( 1 minutes  35.051 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  546.133347      546.133347   188.321838
+    0     256.0  546.133347      546.133347   186.181817
     1     384.0  614.400016      585.142862   153.600004
     2     512.0  655.360017      606.814814   154.566038
-    3     640.0  706.206879      640.000002   160.000000
+    3     640.0  706.206879      640.000002   158.759699
     4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
     93  12160.0  812.359066      406.179533   198.936606
     94  12288.0  812.429770      415.661740   199.197579
     95  12416.0  812.498981      412.149375   198.854847
-    96  12544.0  810.925276      412.546756   199.111113
+    96  12544.0  810.925276      412.971190   199.111113
     97  12672.0  811.007961      412.097543   199.167004
 
     [98 rows x 4 columns]
@@ -306,7 +306,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  27.135 seconds)
+   **Total running time of the script:** ( 3 minutes  28.987 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -459,37 +459,37 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
 
     matmul-performance:
              M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
-    0    256.0   2.978909  ...   2.978909              3.276800
-    1    384.0   7.372800  ...   7.899428              7.899428
-    2    512.0  14.563555  ...  16.384000             15.420235
+    0    256.0   2.978909  ...   2.978909              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  39.025776  ...  40.140799             39.025776
     6   1024.0  49.932191  ...  53.773130             52.428801
     7   1152.0  44.566925  ...  47.396572             47.396572
-    8   1280.0  51.200001  ...  57.690139             57.690139
+    8   1280.0  51.200001  ...  57.690139             56.888887
     9   1408.0  64.138541  ...  68.147202             67.305878
-    10  1536.0  80.430545  ...  81.355034             79.526831
+    10  1536.0  80.430545  ...  81.355034             78.643199
     11  1664.0  62.929456  ...  63.372618             62.492442
     12  1792.0  72.512412  ...  73.460287             59.467852
-    13  1920.0  68.776119  ...  71.626943             71.257735
+    13  1920.0  69.120002  ...  71.257735             71.257735
     14  2048.0  73.908442  ...  78.398206             77.314362
-    15  2176.0  83.155572  ...  87.876193             85.998493
-    16  2304.0  68.446623  ...  78.064941             77.057651
-    17  2432.0  71.305746  ...  84.367759             75.320281
+    15  2176.0  83.155572  ...  87.876193             86.367588
+    16  2304.0  68.446623  ...  78.064941             77.307030
+    17  2432.0  71.305746  ...  86.179335             75.118889
     18  2560.0  77.833728  ...  82.747477             81.715711
-    19  2688.0  83.552988  ...  90.966561             89.676257
-    20  2816.0  79.443003  ...  84.523664             83.873477
-    21  2944.0  82.509987  ...  83.337844             82.373605
-    22  3072.0  81.707223  ...  89.310890             89.030036
-    23  3200.0  84.656085  ...  96.530922             94.674553
-    24  3328.0  82.369902  ...  85.398926             85.096096
-    25  3456.0  82.099354  ...  91.824110             90.382926
-    26  3584.0  85.633710  ...  98.375705             98.591437
-    27  3712.0  84.230479  ...  87.783251             82.559787
-    28  3840.0  84.100380  ...  93.563449             84.484863
-    29  3968.0  92.512459  ...  84.976733             91.540836
-    30  4096.0  87.495257  ...  88.127204             91.242506
+    19  2688.0  83.277839  ...  90.532356             88.628636
+    20  2816.0  79.011245  ...  83.712490             83.074685
+    21  2944.0  82.102191  ...  83.337844             82.102191
+    22  3072.0  81.825298  ...  88.890270             88.060814
+    23  3200.0  83.660130  ...  96.096095             92.888243
+    24  3328.0  83.226931  ...  85.500351             84.596116
+    25  3456.0  81.108217  ...  91.771848             85.676480
+    26  3584.0  85.633710  ...  97.416461             97.734120
+    27  3712.0  85.455380  ...  89.194055             87.783251
+    28  3840.0  80.284573  ...  86.197974             89.912191
+    29  3968.0  88.873953  ...  91.747320             84.328915
+    30  4096.0  92.820009  ...  83.055527             89.958266
 
     [31 rows x 5 columns]
 
@@ -499,7 +499,7 @@ 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  30.888 seconds)
+   **Total running time of the script:** ( 6 minutes  31.599 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

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

@@ -40,34 +40,34 @@ Layer Normalization
               N      Triton       Torch        Apex
     0    1024.0  585.142849  277.694907  468.114273
     1    1536.0  630.153868  323.368435  511.999982
-    2    2048.0  668.734716  334.367358  520.126988
+    2    2048.0  682.666643  334.367358  520.126988
     3    2560.0  694.237267  365.714281  512.000013
     4    3072.0  712.347810  378.092307  496.484863
-    5    3584.0  725.873439  384.859062  448.000001
-    6    4096.0  728.177767  381.023256  445.823133
-    7    4608.0  670.254540  394.267384  421.302872
-    8    5120.0  688.403381  397.669909  424.455959
-    9    5632.0  698.542675  395.228063  411.470331
-    10   6144.0  702.171410  402.885254  411.313806
-    11   6656.0  700.631610  398.861429  400.360920
+    5    3584.0  725.873439  384.859062  451.527536
+    6    4096.0  728.177767  381.023256  455.111095
+    7    4608.0  670.254540  394.267384  426.173427
+    8    5120.0  688.403381  397.669909  420.102563
+    9    5632.0  704.000002  395.228063  415.262685
+    10   6144.0  697.191505  402.885254  409.600010
+    11   6656.0  700.631610  400.360920  400.360920
     12   7168.0  690.891575  396.844306  387.459443
     13   7680.0  678.895043  393.846167  386.415087
     14   8192.0  636.271854  393.609605  371.308771
-    15   8704.0  627.315309  389.005597  380.502740
-    16   9216.0  606.814809  407.337026  383.999986
-    17   9728.0  587.350922  409.599987  383.369452
-    18  10240.0  564.965524  408.578556  381.911416
+    15   8704.0  624.502255  389.005597  380.502740
+    16   9216.0  604.327881  407.337026  383.999986
+    17   9728.0  585.142883  409.599987  383.369452
+    18  10240.0  564.965524  408.578556  382.803739
     19  10752.0  546.133312  411.559798  381.445676
     20  11264.0  533.207081  406.826188  373.134567
     21  11776.0  520.486200  409.599991  377.587162
-    22  12288.0  513.336807  413.911572  383.251457
+    22  12288.0  516.031509  413.911572  383.251457
     23  12800.0  504.433489  410.420828  376.470582
     24  13312.0  494.180982  405.699062  376.976995
     25  13824.0  482.934503  411.888257  379.389355
     26  14336.0  471.967074  406.695045  374.185964
     27  14848.0  461.297068  408.192434  375.304904
     28  15360.0  454.269882  406.214870  378.092307
-    29  15872.0  447.098578  406.974373  376.783377
+    29  15872.0  447.887117  406.974373  376.225175
 
 
 
@@ -393,7 +393,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  36.789 seconds)
+   **Total running time of the script:** ( 5 minutes  32.190 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

master/_sources/getting-started/tutorials/06-fused-attention.rst.txt

@@ -390,7 +390,7 @@ This is a Triton implementation of the Flash Attention algorithm
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  0.071 seconds)
+   **Total running time of the script:** ( 0 minutes  0.075 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_06-fused-attention.py:

master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt

@@ -152,7 +152,7 @@ We can also customize the libdevice library path by passing the path to the `lib
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  0.010 seconds)
+   **Total running time of the script:** ( 0 minutes  0.012 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_07-libdevice-function.py:

master/_sources/getting-started/tutorials/sg_execution_times.rst.txt

@@ -5,20 +5,20 @@
 
 Computation times
 =================
-**17:20.953** total execution time for **getting-started_tutorials** files:
+**17:07.926** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:30.888 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:31.599 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:36.789 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:32.190 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:27.135 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:28.987 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:46.048 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:35.051 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``)             | 00:00.071 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``)             | 00:00.075 | 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_07-libdevice-function.py` (``07-libdevice-function.py``)       | 00:00.010 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``)       | 00:00.012 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -327,7 +327,7 @@ 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
@@ -337,12 +337,12 @@ for different problem sizes.</p>
 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  46.048 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  35.051 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

@@ -371,16 +371,16 @@ 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  546.133347      546.133347   188.321838
+0     256.0  546.133347      546.133347   186.181817
 1     384.0  614.400016      585.142862   153.600004
 2     512.0  655.360017      606.814814   154.566038
-3     640.0  706.206879      640.000002   160.000000
+3     640.0  706.206879      640.000002   158.759699
 4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
 93  12160.0  812.359066      406.179533   198.936606
 94  12288.0  812.429770      415.661740   199.197579
 95  12416.0  812.498981      412.149375   198.854847
-96  12544.0  810.925276      412.546756   199.111113
+96  12544.0  810.925276      412.971190   199.111113
 97  12672.0  811.007961      412.097543   199.167004
 
 [98 rows x 4 columns]
@@ -394,7 +394,7 @@ 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  27.135 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  28.987 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

@@ -567,42 +567,42 @@ torch_output=tensor([[  1.1045, -36.9688,  31.4688,  ..., -11.3906,  24.4531, -3
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>matmul-performance:
          M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
-0    256.0   2.978909  ...   2.978909              3.276800
-1    384.0   7.372800  ...   7.899428              7.899428
-2    512.0  14.563555  ...  16.384000             15.420235
+0    256.0   2.978909  ...   2.978909              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  39.025776  ...  40.140799             39.025776
 6   1024.0  49.932191  ...  53.773130             52.428801
 7   1152.0  44.566925  ...  47.396572             47.396572
-8   1280.0  51.200001  ...  57.690139             57.690139
+8   1280.0  51.200001  ...  57.690139             56.888887
 9   1408.0  64.138541  ...  68.147202             67.305878
-10  1536.0  80.430545  ...  81.355034             79.526831
+10  1536.0  80.430545  ...  81.355034             78.643199
 11  1664.0  62.929456  ...  63.372618             62.492442
 12  1792.0  72.512412  ...  73.460287             59.467852
-13  1920.0  68.776119  ...  71.626943             71.257735
+13  1920.0  69.120002  ...  71.257735             71.257735
 14  2048.0  73.908442  ...  78.398206             77.314362
-15  2176.0  83.155572  ...  87.876193             85.998493
-16  2304.0  68.446623  ...  78.064941             77.057651
-17  2432.0  71.305746  ...  84.367759             75.320281
+15  2176.0  83.155572  ...  87.876193             86.367588
+16  2304.0  68.446623  ...  78.064941             77.307030
+17  2432.0  71.305746  ...  86.179335             75.118889
 18  2560.0  77.833728  ...  82.747477             81.715711
-19  2688.0  83.552988  ...  90.966561             89.676257
-20  2816.0  79.443003  ...  84.523664             83.873477
-21  2944.0  82.509987  ...  83.337844             82.373605
-22  3072.0  81.707223  ...  89.310890             89.030036
-23  3200.0  84.656085  ...  96.530922             94.674553
-24  3328.0  82.369902  ...  85.398926             85.096096
-25  3456.0  82.099354  ...  91.824110             90.382926
-26  3584.0  85.633710  ...  98.375705             98.591437
-27  3712.0  84.230479  ...  87.783251             82.559787
-28  3840.0  84.100380  ...  93.563449             84.484863
-29  3968.0  92.512459  ...  84.976733             91.540836
-30  4096.0  87.495257  ...  88.127204             91.242506
+19  2688.0  83.277839  ...  90.532356             88.628636
+20  2816.0  79.011245  ...  83.712490             83.074685
+21  2944.0  82.102191  ...  83.337844             82.102191
+22  3072.0  81.825298  ...  88.890270             88.060814
+23  3200.0  83.660130  ...  96.096095             92.888243
+24  3328.0  83.226931  ...  85.500351             84.596116
+25  3456.0  81.108217  ...  91.771848             85.676480
+26  3584.0  85.633710  ...  97.416461             97.734120
+27  3712.0  85.455380  ...  89.194055             87.783251
+28  3840.0  80.284573  ...  86.197974             89.912191
+29  3968.0  88.873953  ...  91.747320             84.328915
+30  4096.0  92.820009  ...  83.055527             89.958266
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  30.888 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  31.599 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/05-layer-norm.html

@@ -198,34 +198,34 @@ to download the full example code</p>
           N      Triton       Torch        Apex
 0    1024.0  585.142849  277.694907  468.114273
 1    1536.0  630.153868  323.368435  511.999982
-2    2048.0  668.734716  334.367358  520.126988
+2    2048.0  682.666643  334.367358  520.126988
 3    2560.0  694.237267  365.714281  512.000013
 4    3072.0  712.347810  378.092307  496.484863
-5    3584.0  725.873439  384.859062  448.000001
-6    4096.0  728.177767  381.023256  445.823133
-7    4608.0  670.254540  394.267384  421.302872
-8    5120.0  688.403381  397.669909  424.455959
-9    5632.0  698.542675  395.228063  411.470331
-10   6144.0  702.171410  402.885254  411.313806
-11   6656.0  700.631610  398.861429  400.360920
+5    3584.0  725.873439  384.859062  451.527536
+6    4096.0  728.177767  381.023256  455.111095
+7    4608.0  670.254540  394.267384  426.173427
+8    5120.0  688.403381  397.669909  420.102563
+9    5632.0  704.000002  395.228063  415.262685
+10   6144.0  697.191505  402.885254  409.600010
+11   6656.0  700.631610  400.360920  400.360920
 12   7168.0  690.891575  396.844306  387.459443
 13   7680.0  678.895043  393.846167  386.415087
 14   8192.0  636.271854  393.609605  371.308771
-15   8704.0  627.315309  389.005597  380.502740
-16   9216.0  606.814809  407.337026  383.999986
-17   9728.0  587.350922  409.599987  383.369452
-18  10240.0  564.965524  408.578556  381.911416
+15   8704.0  624.502255  389.005597  380.502740
+16   9216.0  604.327881  407.337026  383.999986
+17   9728.0  585.142883  409.599987  383.369452
+18  10240.0  564.965524  408.578556  382.803739
 19  10752.0  546.133312  411.559798  381.445676
 20  11264.0  533.207081  406.826188  373.134567
 21  11776.0  520.486200  409.599991  377.587162
-22  12288.0  513.336807  413.911572  383.251457
+22  12288.0  516.031509  413.911572  383.251457
 23  12800.0  504.433489  410.420828  376.470582
 24  13312.0  494.180982  405.699062  376.976995
 25  13824.0  482.934503  411.888257  379.389355
 26  14336.0  471.967074  406.695045  374.185964
 27  14848.0  461.297068  408.192434  375.304904
 28  15360.0  454.269882  406.214870  378.092307
-29  15872.0  447.098578  406.974373  376.783377
+29  15872.0  447.887117  406.974373  376.225175
 </pre></div>
 </div>
 <div class="line-block">
@@ -543,7 +543,7 @@ 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> ( 5 minutes  36.789 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  32.190 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/06-fused-attention.html

@@ -548,7 +548,7 @@ to download the full example code</p>
 <span class="c1"># bench_flash_attention.run(save_path=&#39;.&#39;, print_data=True)</span>
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.071 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.075 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-06-fused-attention-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/54a35f6ec55f9746935b9566fb6bb1df/06-fused-attention.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">06-fused-attention.py</span></code></a></p>

master/getting-started/tutorials/07-libdevice-function.html

@@ -276,7 +276,7 @@ tensor([0.4105, 0.5430, 0.0249,  ..., 0.0424, 0.5351, 0.8149], device='cuda:
 The maximum difference between torch and triton is 2.384185791015625e-07
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.010 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.012 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-07-libdevice-function-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/3ff29f967ace7985da24aab10352fc76/07-libdevice-function.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">07-libdevice-function.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>17:20.953</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>17:07.926</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>06:30.888</p></td>
+<td><p>06:31.599</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><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>05:36.789</p></td>
+<td><p>05:32.190</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><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>03:27.135</p></td>
+<td><p>03:28.987</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="01-vector-add.html#sphx-glr-getting-started-tutorials-01-vector-add-py"><span class="std std-ref">Vector Addition</span></a> (<code class="docutils literal notranslate"><span class="pre">01-vector-add.py</span></code>)</p></td>
-<td><p>01:46.048</p></td>
+<td><p>01:35.051</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="06-fused-attention.html#sphx-glr-getting-started-tutorials-06-fused-attention-py"><span class="std std-ref">Fused Attention</span></a> (<code class="docutils literal notranslate"><span class="pre">06-fused-attention.py</span></code>)</p></td>
-<td><p>00:00.071</p></td>
+<td><p>00:00.075</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><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>
@@ -207,7 +207,7 @@
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="07-libdevice-function.html#sphx-glr-getting-started-tutorials-07-libdevice-function-py"><span class="std std-ref">Libdevice function</span></a> (<code class="docutils literal notranslate"><span class="pre">07-libdevice-function.py</span></code>)</p></td>
-<td><p>00:00.010</p></td>
+<td><p>00:00.012</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: 9550e7e67a618ab8fb2356063f9a5dc6
+config: 2d5a1488528d834fcf88480396421fec
 tags: 645f666f9bcd5a90fca523b33c5a78b7