[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: 53dd097a7168e06dae1f9b4d065b8571
+config: ba5b0fb41fda44af3389f4f24cc39268
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -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  41.917 seconds)
+   **Total running time of the script:** ( 1 minutes  47.895 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

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

@@ -278,17 +278,17 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
 
     softmax-performance:
               N      Triton  Torch (native)  Torch (jit)
-    0     256.0  512.000001      546.133347   190.511628
+    0     256.0  512.000001      546.133347   186.181817
     1     384.0  614.400016      585.142862   153.600004
-    2     512.0  655.360017      585.142849   154.566038
+    2     512.0  655.360017      606.814814   154.566038
     3     640.0  706.206879      640.000002   160.000000
     4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
-    93  12160.0  812.359066      406.603966   199.038365
-    94  12288.0  812.429770      416.101597   199.197579
-    95  12416.0  812.498981      413.006241   198.854847
-    96  12544.0  810.925276      412.971190   199.111113
-    97  12672.0  811.007961      412.516771   199.167004
+    93  12160.0  812.359066      406.179533   198.834951
+    94  12288.0  812.429770      415.661740   199.197579
+    95  12416.0  812.498981      412.149375   198.655991
+    96  12544.0  810.925276      412.971190   198.913776
+    97  12672.0  811.007961      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  30.054 seconds)
+   **Total running time of the script:** ( 3 minutes  31.309 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   2.730667  ...   2.978909              2.978909
-    1    384.0   7.372800  ...   8.507077              8.507077
-    2    512.0  14.563555  ...  15.420235             16.384000
+    0    256.0   2.730667  ...   3.276800              3.276800
+    1    384.0   7.372800  ...   7.899428              7.899428
+    2    512.0  14.563555  ...  16.384000             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             39.025776
+    5    896.0  39.025776  ...  40.140799             39.025776
     6   1024.0  49.932191  ...  53.773130             52.428801
-    7   1152.0  45.242181  ...  48.161033             47.396572
+    7   1152.0  44.566925  ...  48.161033             47.396572
     8   1280.0  51.200001  ...  57.690139             57.690139
     9   1408.0  64.138541  ...  69.009825             68.147202
-    10  1536.0  80.430545  ...  80.430545             78.643199
-    11  1664.0  62.929456  ...  63.372618             62.492442
-    12  1792.0  72.983276  ...  73.460287             59.467852
-    13  1920.0  69.120002  ...  71.626943             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             77.307030
-    17  2432.0  71.305746  ...  86.179335             85.653855
-    18  2560.0  77.833728  ...  82.539044             81.310171
-    19  2688.0  83.737433  ...  90.532356             89.676257
-    20  2816.0  80.767055  ...  83.873477             81.674548
-    21  2944.0  82.237674  ...  83.477440             82.373605
-    22  3072.0  81.707223  ...  89.877939             88.197981
-    23  3200.0  84.544253  ...  96.822991             94.814812
-    24  3328.0  83.226931  ...  85.398926             84.895397
-    25  3456.0  81.766291  ...  91.511426             86.503829
-    26  3584.0  83.876297  ...  95.756542             95.350361
-    27  3712.0  84.159518  ...  88.837126             87.937800
-    28  3840.0  85.070769  ...  93.326587             85.663823
-    29  3968.0  91.198760  ...  87.097744             91.609561
-    30  4096.0  86.204508  ...  93.792965             89.240508
+    10  1536.0  80.430545  ...  81.355034             79.526831
+    11  1664.0  63.372618  ...  63.372618             62.492442
+    12  1792.0  72.983276  ...  73.943582             59.467852
+    13  1920.0  69.467336  ...  71.257735             71.257735
+    14  2048.0  73.584279  ...  78.398206             77.314362
+    15  2176.0  83.500614  ...  87.876193             86.367588
+    16  2304.0  68.251065  ...  78.064941             77.307030
+    17  2432.0  71.305746  ...  86.444504             84.621881
+    18  2560.0  78.019048  ...  82.331658             81.108913
+    19  2688.0  83.369354  ...  90.966561             89.464755
+    20  2816.0  79.587973  ...  84.197315             83.074685
+    21  2944.0  81.967162  ...  83.060049             82.784108
+    22  3072.0  82.420822  ...  87.924073             85.019675
+    23  3200.0  84.768213  ...  96.458178             95.238096
+    24  3328.0  83.905938  ...  85.096096             84.298943
+    25  3456.0  82.604067  ...  91.304157             87.442050
+    26  3584.0  87.211821  ...  98.375705             91.656871
+    27  3712.0  84.874549  ...  89.035062             86.044224
+    28  3840.0  84.744825  ...  93.484358             84.484863
+    29  3968.0  92.582651  ...  84.976733             91.472214
+    30  4096.0  86.256445  ...  88.475759             90.230403
 
     [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  38.507 seconds)
+   **Total running time of the script:** ( 6 minutes  18.355 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  682.666643  337.814445  520.126988
+    2    2048.0  668.734716  334.367358  520.126988
     3    2560.0  694.237267  362.477870  512.000013
-    4    3072.0  712.347810  378.092307  501.551037
-    5    3584.0  725.873439  384.859062  451.527536
-    6    4096.0  728.177767  381.023256  451.972420
-    7    4608.0  670.254540  396.387087  428.651163
-    8    5120.0  688.403381  397.669909  420.102563
-    9    5632.0  704.000002  395.228063  413.357796
-    10   6144.0  702.171410  402.885254  413.042029
-    11   6656.0  700.631610  400.360920  400.360920
-    12   7168.0  690.891575  392.767108  382.293315
-    13   7680.0  678.895043  393.846167  386.415087
-    14   8192.0  636.271854  394.795186  377.729113
-    15   8704.0  624.502255  389.005597  379.465939
-    16   9216.0  604.327881  406.214877  382.010363
+    4    3072.0  712.347810  378.092307  496.484863
+    5    3584.0  725.873439  384.859062  455.111115
+    6    4096.0  728.177767  381.023256  442.810792
+    7    4608.0  670.254540  394.267384  426.173427
+    8    5120.0  688.403381  397.669909  426.666652
+    9    5632.0  698.542675  395.228063  409.599997
+    10   6144.0  702.171410  402.885254  411.313806
+    11   6656.0  700.631610  398.861429  400.360920
+    12   7168.0  686.754468  394.116833  387.459443
+    13   7680.0  678.895043  392.587863  386.415087
+    14   8192.0  633.198054  387.786968  369.216905
+    15   8704.0  624.502255  387.922008  379.465939
+    16   9216.0  604.327881  406.214877  383.002605
     17   9728.0  585.142883  408.524944  383.369452
     18  10240.0  564.965524  409.600010  382.803739
-    19  10752.0  546.133312  411.559798  380.601764
-    20  11264.0  531.634232  404.997742  371.595879
-    21  11776.0  520.486200  409.599991  377.587162
+    19  10752.0  546.133312  410.577576  381.445676
+    20  11264.0  531.634232  406.826188  374.686074
+    21  11776.0  520.486200  409.599991  376.831982
     22  12288.0  516.031509  413.911572  383.251457
-    23  12800.0  504.433489  409.599981  377.163903
-    24  13312.0  494.180982  406.473303  377.645399
-    25  13824.0  482.934503  412.656711  379.389355
-    26  14336.0  471.967074  402.414053  370.558967
-    27  14848.0  461.297068  407.492270  373.534584
-    28  15360.0  454.269882  406.214870  377.511515
-    29  15872.0  447.098578  409.599996  377.343238
+    23  12800.0  504.433489  409.599981  376.470582
+    24  13312.0  494.180982  405.699062  376.976995
+    25  13824.0  481.882350  412.656711  379.389355
+    26  14336.0  471.967074  405.975225  372.969090
+    27  14848.0  461.297068  406.794504  375.304904
+    28  15360.0  454.269882  406.887417  377.511515
+    29  15872.0  447.098578  406.974373  376.225175
 
 
 
@@ -393,7 +393,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  37.218 seconds)
+   **Total running time of the script:** ( 5 minutes  33.735 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  0.073 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  0.011 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
 =================
-**17:27.791** total execution time for **getting-started_tutorials** files:
+**17:11.392** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:38.507 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:18.355 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:37.218 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:33.735 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:30.054 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:31.309 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:41.917 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:47.895 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``)             | 00:00.073 | 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``)       | 00:00.011 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -342,7 +342,7 @@ 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  41.917 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  47.895 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

@@ -371,17 +371,17 @@ We will then compare its performance against (1) <code class="code docutils lite
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>softmax-performance:
           N      Triton  Torch (native)  Torch (jit)
-0     256.0  512.000001      546.133347   190.511628
+0     256.0  512.000001      546.133347   186.181817
 1     384.0  614.400016      585.142862   153.600004
-2     512.0  655.360017      585.142849   154.566038
+2     512.0  655.360017      606.814814   154.566038
 3     640.0  706.206879      640.000002   160.000000
 4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
-93  12160.0  812.359066      406.603966   199.038365
-94  12288.0  812.429770      416.101597   199.197579
-95  12416.0  812.498981      413.006241   198.854847
-96  12544.0  810.925276      412.971190   199.111113
-97  12672.0  811.007961      412.516771   199.167004
+93  12160.0  812.359066      406.179533   198.834951
+94  12288.0  812.429770      415.661740   199.197579
+95  12416.0  812.498981      412.149375   198.655991
+96  12544.0  810.925276      412.971190   198.913776
+97  12672.0  811.007961      411.679167   198.971549
 
 [98 rows x 4 columns]
 </pre></div>
@@ -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  30.054 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  31.309 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   2.730667  ...   2.978909              2.978909
-1    384.0   7.372800  ...   8.507077              8.507077
-2    512.0  14.563555  ...  15.420235             16.384000
+0    256.0   2.730667  ...   3.276800              3.276800
+1    384.0   7.372800  ...   7.899428              7.899428
+2    512.0  14.563555  ...  16.384000             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             39.025776
+5    896.0  39.025776  ...  40.140799             39.025776
 6   1024.0  49.932191  ...  53.773130             52.428801
-7   1152.0  45.242181  ...  48.161033             47.396572
+7   1152.0  44.566925  ...  48.161033             47.396572
 8   1280.0  51.200001  ...  57.690139             57.690139
 9   1408.0  64.138541  ...  69.009825             68.147202
-10  1536.0  80.430545  ...  80.430545             78.643199
-11  1664.0  62.929456  ...  63.372618             62.492442
-12  1792.0  72.983276  ...  73.460287             59.467852
-13  1920.0  69.120002  ...  71.626943             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             77.307030
-17  2432.0  71.305746  ...  86.179335             85.653855
-18  2560.0  77.833728  ...  82.539044             81.310171
-19  2688.0  83.737433  ...  90.532356             89.676257
-20  2816.0  80.767055  ...  83.873477             81.674548
-21  2944.0  82.237674  ...  83.477440             82.373605
-22  3072.0  81.707223  ...  89.877939             88.197981
-23  3200.0  84.544253  ...  96.822991             94.814812
-24  3328.0  83.226931  ...  85.398926             84.895397
-25  3456.0  81.766291  ...  91.511426             86.503829
-26  3584.0  83.876297  ...  95.756542             95.350361
-27  3712.0  84.159518  ...  88.837126             87.937800
-28  3840.0  85.070769  ...  93.326587             85.663823
-29  3968.0  91.198760  ...  87.097744             91.609561
-30  4096.0  86.204508  ...  93.792965             89.240508
+10  1536.0  80.430545  ...  81.355034             79.526831
+11  1664.0  63.372618  ...  63.372618             62.492442
+12  1792.0  72.983276  ...  73.943582             59.467852
+13  1920.0  69.467336  ...  71.257735             71.257735
+14  2048.0  73.584279  ...  78.398206             77.314362
+15  2176.0  83.500614  ...  87.876193             86.367588
+16  2304.0  68.251065  ...  78.064941             77.307030
+17  2432.0  71.305746  ...  86.444504             84.621881
+18  2560.0  78.019048  ...  82.331658             81.108913
+19  2688.0  83.369354  ...  90.966561             89.464755
+20  2816.0  79.587973  ...  84.197315             83.074685
+21  2944.0  81.967162  ...  83.060049             82.784108
+22  3072.0  82.420822  ...  87.924073             85.019675
+23  3200.0  84.768213  ...  96.458178             95.238096
+24  3328.0  83.905938  ...  85.096096             84.298943
+25  3456.0  82.604067  ...  91.304157             87.442050
+26  3584.0  87.211821  ...  98.375705             91.656871
+27  3712.0  84.874549  ...  89.035062             86.044224
+28  3840.0  84.744825  ...  93.484358             84.484863
+29  3968.0  92.582651  ...  84.976733             91.472214
+30  4096.0  86.256445  ...  88.475759             90.230403
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  38.507 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  18.355 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  682.666643  337.814445  520.126988
+2    2048.0  668.734716  334.367358  520.126988
 3    2560.0  694.237267  362.477870  512.000013
-4    3072.0  712.347810  378.092307  501.551037
-5    3584.0  725.873439  384.859062  451.527536
-6    4096.0  728.177767  381.023256  451.972420
-7    4608.0  670.254540  396.387087  428.651163
-8    5120.0  688.403381  397.669909  420.102563
-9    5632.0  704.000002  395.228063  413.357796
-10   6144.0  702.171410  402.885254  413.042029
-11   6656.0  700.631610  400.360920  400.360920
-12   7168.0  690.891575  392.767108  382.293315
-13   7680.0  678.895043  393.846167  386.415087
-14   8192.0  636.271854  394.795186  377.729113
-15   8704.0  624.502255  389.005597  379.465939
-16   9216.0  604.327881  406.214877  382.010363
+4    3072.0  712.347810  378.092307  496.484863
+5    3584.0  725.873439  384.859062  455.111115
+6    4096.0  728.177767  381.023256  442.810792
+7    4608.0  670.254540  394.267384  426.173427
+8    5120.0  688.403381  397.669909  426.666652
+9    5632.0  698.542675  395.228063  409.599997
+10   6144.0  702.171410  402.885254  411.313806
+11   6656.0  700.631610  398.861429  400.360920
+12   7168.0  686.754468  394.116833  387.459443
+13   7680.0  678.895043  392.587863  386.415087
+14   8192.0  633.198054  387.786968  369.216905
+15   8704.0  624.502255  387.922008  379.465939
+16   9216.0  604.327881  406.214877  383.002605
 17   9728.0  585.142883  408.524944  383.369452
 18  10240.0  564.965524  409.600010  382.803739
-19  10752.0  546.133312  411.559798  380.601764
-20  11264.0  531.634232  404.997742  371.595879
-21  11776.0  520.486200  409.599991  377.587162
+19  10752.0  546.133312  410.577576  381.445676
+20  11264.0  531.634232  406.826188  374.686074
+21  11776.0  520.486200  409.599991  376.831982
 22  12288.0  516.031509  413.911572  383.251457
-23  12800.0  504.433489  409.599981  377.163903
-24  13312.0  494.180982  406.473303  377.645399
-25  13824.0  482.934503  412.656711  379.389355
-26  14336.0  471.967074  402.414053  370.558967
-27  14848.0  461.297068  407.492270  373.534584
-28  15360.0  454.269882  406.214870  377.511515
-29  15872.0  447.098578  409.599996  377.343238
+23  12800.0  504.433489  409.599981  376.470582
+24  13312.0  494.180982  405.699062  376.976995
+25  13824.0  481.882350  412.656711  379.389355
+26  14336.0  471.967074  405.975225  372.969090
+27  14848.0  461.297068  406.794504  375.304904
+28  15360.0  454.269882  406.887417  377.511515
+29  15872.0  447.098578  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  37.218 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  33.735 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  0.073 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  0.011 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>17:27.791</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>17:11.392</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>06:38.507</p></td>
+<td><p>06:18.355</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>05:37.218</p></td>
+<td><p>05:33.735</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>03:30.054</p></td>
+<td><p>03:31.309</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>01:41.917</p></td>
+<td><p>01:47.895</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>00:00.073</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>00:00.011</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: 8b4cb503314520bbb947ce2280556d68
+config: e8aec65ae31029828cb789de30606264
 tags: 645f666f9bcd5a90fca523b33c5a78b7