[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: 32cbfb8a2f670efaef501b904c7bd51b
+config: 43dd2d33a5d2138d26dc415193c66c45
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -234,11 +234,11 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
                size      Triton       Torch
     0        4096.0    9.600000    9.600000
     1        8192.0   19.200000   19.200000
-    2       16384.0   38.400001   38.400001
+    2       16384.0   31.999999   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  384.000001
+    6      262144.0  384.000001  341.333321
     7      524288.0  472.615390  472.615390
     8     1048576.0  614.400016  614.400016
     9     2097152.0  722.823517  722.823517
@@ -255,7 +255,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  40.569 seconds)
+   **Total running time of the script:** ( 1 minutes  44.610 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      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
     4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
     93  12160.0  812.359066      406.179533   198.530610
-    94  12288.0  812.429770      415.661740   198.794749
+    94  12288.0  812.429770      416.101597   198.895304
     95  12416.0  812.498981      412.149375   198.457532
-    96  12544.0  812.566838      412.971190   198.716830
+    96  12544.0  810.925276      412.971190   198.766042
-    97  12672.0  812.633240      412.097543   198.776477
+    97  12672.0  811.007961      412.097543   198.873965
 
     [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  26.870 seconds)
+   **Total running time of the script:** ( 3 minutes  31.794 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
+    0    256.0   2.730667  ...   3.276800              2.978909
     1    384.0   7.372800  ...   8.507077              8.507077
     2    512.0  14.563555  ...  16.384000             16.384000
     3    640.0  22.260869  ...  24.380953             24.380953
     4    768.0  32.768000  ...  35.389441             34.028308
     5    896.0  39.025776  ...  40.140799             39.025776
-    6   1024.0  51.150050  ...  53.773130             52.428801
+    6   1024.0  49.932191  ...  53.773130             52.428801
-    7   1152.0  45.242181  ...  48.161033             48.161033
+    7   1152.0  44.566925  ...  47.396572             47.396572
     8   1280.0  51.200001  ...  57.690139             57.690139
-    9   1408.0  64.138541  ...  69.009825             68.147202
+    9   1408.0  64.138541  ...  68.147202             67.305878
-    10  1536.0  81.355034  ...  81.355034             79.526831
+    10  1536.0  80.430545  ...  81.355034             78.643199
-    11  1664.0  63.372618  ...  63.822072             62.929456
+    11  1664.0  62.929456  ...  63.372618             62.492442
-    12  1792.0  72.983276  ...  73.460287             59.467852
+    12  1792.0  72.512412  ...  73.460287             59.467852
-    13  1920.0  68.776119  ...  71.257735             71.257735
+    13  1920.0  69.120002  ...  71.626943             71.257735
     14  2048.0  73.908442  ...  78.398206             77.314362
-    15  2176.0  83.500614  ...  87.494120             85.998493
+    15  2176.0  83.500614  ...  87.876193             86.367588
-    16  2304.0  68.446623  ...  78.064941             77.057651
+    16  2304.0  68.446623  ...  78.064941             77.307030
-    17  2432.0  71.305746  ...  86.444504             75.320281
+    17  2432.0  71.305746  ...  86.711310             85.653855
-    18  2560.0  77.833728  ...  82.747477             81.715711
+    18  2560.0  78.019048  ...  82.747477             81.715711
-    19  2688.0  83.277839  ...  90.532356             90.102270
+    19  2688.0  83.737433  ...  91.185232             89.464755
-    20  2816.0  80.320825  ...  83.873477             83.074685
+    20  2816.0  83.074685  ...  84.687779             83.712490
-    21  2944.0  81.698415  ...  80.510553             83.337844
+    21  2944.0  82.102191  ...  81.034195             82.784108
-    22  3072.0  81.472093  ...  89.735509             88.890270
+    22  3072.0  82.540970  ...  89.170242             87.516392
-    23  3200.0  84.099871  ...  96.749806             95.665176
+    23  3200.0  84.432717  ...  96.822991             95.808380
-    24  3328.0  83.130825  ...  85.297742             84.596116
+    24  3328.0  83.130825  ...  85.500351             84.447271
-    25  3456.0  81.394821  ...  92.138932             90.790053
+    25  3456.0  81.974138  ...  91.719645             90.079964
-    26  3584.0  86.623693  ...  93.370085             96.787292
+    26  3584.0  83.876297  ...  90.549237             94.847460
-    27  3712.0  85.528545  ...  86.641231             87.937800
+    27  3712.0  85.601834  ...  81.285505             86.044224
-    28  3840.0  83.402717  ...  92.429584             85.996889
+    28  3840.0  82.840447  ...  92.236860             86.130841
-    29  3968.0  92.864488  ...  80.120775             84.915752
+    29  3968.0  93.148045  ...  80.120775             84.856701
-    30  4096.0  86.204508  ...  89.062862             90.565269
+    30  4096.0  86.258181  ...  85.762979             90.565269
 
     [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  24.066 seconds)
+   **Total running time of the script:** ( 6 minutes  45.893 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  0.011 seconds)
+   **Total running time of the script:** ( 0 minutes  0.012 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

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

@@ -41,23 +41,23 @@ Layer Normalization
     0    1024.0  585.142849  277.694907  468.114273
     1    1536.0  630.153868  323.368435  511.999982
     2    2048.0  682.666643  334.367358  520.126988
-    3    2560.0  694.237267  365.714281  512.000013
+    3    2560.0  694.237267  365.714281  518.481028
     4    3072.0  712.347810  378.092307  496.484863
     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
+    7    4608.0  670.254540  394.267384  421.302872
-    8    5120.0  688.403381  397.669909  422.268057
+    8    5120.0  688.403381  397.669909  424.455959
-    9    5632.0  704.000002  396.969169  415.262685
+    9    5632.0  704.000002  395.228063  411.470331
     10   6144.0  697.191505  402.885254  409.600010
-    11   6656.0  705.271522  400.360920  400.360920
+    11   6656.0  700.631610  400.360920  400.360920
-    12   7168.0  686.754468  396.844306  386.154893
+    12   7168.0  686.754468  396.844306  387.459443
     13   7680.0  682.666656  393.846167  386.415087
     14   8192.0  636.271854  393.609605  371.308771
-    15   8704.0  627.315309  389.005597  380.502740
+    15   8704.0  627.315309  389.005597  381.545190
     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  382.803739
-    19  10752.0  547.872604  411.559798  381.445676
+    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  514.680630  413.911572  383.251457
@@ -67,7 +67,7 @@ Layer Normalization
     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  376.225175
+    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  37.521 seconds)
+   **Total running time of the script:** ( 5 minutes  39.453 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  0.072 seconds)
+   **Total running time of the script:** ( 0 minutes  0.073 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
 =================
-**17:09.118** total execution time for **getting-started_tutorials** files:
+**17:41.846** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:24.066 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:45.893 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:37.521 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:39.453 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:26.870 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:31.794 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:40.569 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:44.610 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``)             | 00:00.072 | 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_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.011 | 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

@@ -326,11 +326,11 @@ for different problem sizes.</p>
            size      Triton       Torch
 0        4096.0    9.600000    9.600000
 1        8192.0   19.200000   19.200000
-2       16384.0   38.400001   38.400001
+2       16384.0   31.999999   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  384.000001
+6      262144.0  384.000001  341.333321
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
 9     2097152.0  722.823517  722.823517
@@ -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  40.569 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  44.610 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  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
 4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
 93  12160.0  812.359066      406.179533   198.530610
-94  12288.0  812.429770      415.661740   198.794749
+94  12288.0  812.429770      416.101597   198.895304
 95  12416.0  812.498981      412.149375   198.457532
-96  12544.0  812.566838      412.971190   198.716830
+96  12544.0  810.925276      412.971190   198.766042
-97  12672.0  812.633240      412.097543   198.776477
+97  12672.0  811.007961      412.097543   198.873965
 
 [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  26.870 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  31.794 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
+0    256.0   2.730667  ...   3.276800              2.978909
 1    384.0   7.372800  ...   8.507077              8.507077
 2    512.0  14.563555  ...  16.384000             16.384000
 3    640.0  22.260869  ...  24.380953             24.380953
 4    768.0  32.768000  ...  35.389441             34.028308
 5    896.0  39.025776  ...  40.140799             39.025776
-6   1024.0  51.150050  ...  53.773130             52.428801
+6   1024.0  49.932191  ...  53.773130             52.428801
-7   1152.0  45.242181  ...  48.161033             48.161033
+7   1152.0  44.566925  ...  47.396572             47.396572
 8   1280.0  51.200001  ...  57.690139             57.690139
-9   1408.0  64.138541  ...  69.009825             68.147202
+9   1408.0  64.138541  ...  68.147202             67.305878
-10  1536.0  81.355034  ...  81.355034             79.526831
+10  1536.0  80.430545  ...  81.355034             78.643199
-11  1664.0  63.372618  ...  63.822072             62.929456
+11  1664.0  62.929456  ...  63.372618             62.492442
-12  1792.0  72.983276  ...  73.460287             59.467852
+12  1792.0  72.512412  ...  73.460287             59.467852
-13  1920.0  68.776119  ...  71.257735             71.257735
+13  1920.0  69.120002  ...  71.626943             71.257735
 14  2048.0  73.908442  ...  78.398206             77.314362
-15  2176.0  83.500614  ...  87.494120             85.998493
+15  2176.0  83.500614  ...  87.876193             86.367588
-16  2304.0  68.446623  ...  78.064941             77.057651
+16  2304.0  68.446623  ...  78.064941             77.307030
-17  2432.0  71.305746  ...  86.444504             75.320281
+17  2432.0  71.305746  ...  86.711310             85.653855
-18  2560.0  77.833728  ...  82.747477             81.715711
+18  2560.0  78.019048  ...  82.747477             81.715711
-19  2688.0  83.277839  ...  90.532356             90.102270
+19  2688.0  83.737433  ...  91.185232             89.464755
-20  2816.0  80.320825  ...  83.873477             83.074685
+20  2816.0  83.074685  ...  84.687779             83.712490
-21  2944.0  81.698415  ...  80.510553             83.337844
+21  2944.0  82.102191  ...  81.034195             82.784108
-22  3072.0  81.472093  ...  89.735509             88.890270
+22  3072.0  82.540970  ...  89.170242             87.516392
-23  3200.0  84.099871  ...  96.749806             95.665176
+23  3200.0  84.432717  ...  96.822991             95.808380
-24  3328.0  83.130825  ...  85.297742             84.596116
+24  3328.0  83.130825  ...  85.500351             84.447271
-25  3456.0  81.394821  ...  92.138932             90.790053
+25  3456.0  81.974138  ...  91.719645             90.079964
-26  3584.0  86.623693  ...  93.370085             96.787292
+26  3584.0  83.876297  ...  90.549237             94.847460
-27  3712.0  85.528545  ...  86.641231             87.937800
+27  3712.0  85.601834  ...  81.285505             86.044224
-28  3840.0  83.402717  ...  92.429584             85.996889
+28  3840.0  82.840447  ...  92.236860             86.130841
-29  3968.0  92.864488  ...  80.120775             84.915752
+29  3968.0  93.148045  ...  80.120775             84.856701
-30  4096.0  86.204508  ...  89.062862             90.565269
+30  4096.0  86.258181  ...  85.762979             90.565269
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  24.066 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  45.893 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

@@ -374,7 +374,7 @@ 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  0.011 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-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

@@ -199,23 +199,23 @@ to download the full example code</p>
 0    1024.0  585.142849  277.694907  468.114273
 1    1536.0  630.153868  323.368435  511.999982
 2    2048.0  682.666643  334.367358  520.126988
-3    2560.0  694.237267  365.714281  512.000013
+3    2560.0  694.237267  365.714281  518.481028
 4    3072.0  712.347810  378.092307  496.484863
 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
+7    4608.0  670.254540  394.267384  421.302872
-8    5120.0  688.403381  397.669909  422.268057
+8    5120.0  688.403381  397.669909  424.455959
-9    5632.0  704.000002  396.969169  415.262685
+9    5632.0  704.000002  395.228063  411.470331
 10   6144.0  697.191505  402.885254  409.600010
-11   6656.0  705.271522  400.360920  400.360920
+11   6656.0  700.631610  400.360920  400.360920
-12   7168.0  686.754468  396.844306  386.154893
+12   7168.0  686.754468  396.844306  387.459443
 13   7680.0  682.666656  393.846167  386.415087
 14   8192.0  636.271854  393.609605  371.308771
-15   8704.0  627.315309  389.005597  380.502740
+15   8704.0  627.315309  389.005597  381.545190
 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  382.803739
-19  10752.0  547.872604  411.559798  381.445676
+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  514.680630  413.911572  383.251457
@@ -225,7 +225,7 @@ to download the full example code</p>
 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  376.225175
+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  37.521 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  39.453 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  0.072 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.073 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>17:09.118</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>17:41.846</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -183,31 +183,31 @@
 </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>06:24.066</p></td>
+<td><p>06:45.893</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>05:37.521</p></td>
+<td><p>05:39.453</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>03:26.870</p></td>
+<td><p>03:31.794</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>01:40.569</p></td>
+<td><p>01:44.610</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>00:00.072</p></td>
+<td><p>00:00.073</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>
-<td><p>00:00.011</p></td>
+<td><p>00:00.012</p></td>
 <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: d293b70a76cc0df6c4aab8f81c001b44
+config: 21dfb08a3a70ef7a55763a3173d19a98
 tags: 645f666f9bcd5a90fca523b33c5a78b7