[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: 1527ee6251a4943877251e7d1521a24b
+config: 0c38725d1eea30310efc3d8896a5a437
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -235,17 +235,17 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     0        4096.0    9.600000    9.600000
     1        8192.0   19.200000   19.200000
     2       16384.0   38.400001   38.400001
-    3       32768.0   63.999998   63.999998
+    3       32768.0   76.800002   76.800002
     4       65536.0  127.999995  127.999995
     5      131072.0  219.428568  219.428568
     6      262144.0  341.333321  384.000001
     7      524288.0  472.615390  472.615390
     8     1048576.0  614.400016  614.400016
-    9     2097152.0  722.823517  702.171410
+    9     2097152.0  722.823517  722.823517
     10    4194304.0  780.190482  780.190482
     11    8388608.0  812.429770  812.429770
     12   16777216.0  833.084721  833.084721
-    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  46.918 seconds)
+   **Total running time of the script:** ( 1 minutes  48.779 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      512.000001   190.511628
+    0     256.0  546.133347      512.000001   190.511628
     1     384.0  614.400016      585.142862   153.600004
     2     512.0  655.360017      585.142849   154.566038
     3     640.0  706.206879      640.000002   158.759699
-    4     768.0  722.823517      664.216187   162.754967
+    4     768.0  722.823517      664.216187   161.684218
     ..      ...         ...             ...          ...
-    93  12160.0  812.359066      406.179533   198.834951
+    93  12160.0  812.359066      406.179533   198.328233
-    94  12288.0  812.429770      415.881552   199.096718
+    94  12288.0  812.429770      415.222812   198.694297
-    95  12416.0  812.498981      412.149375   198.755369
+    95  12416.0  812.498981      411.722274   198.358474
-    96  12544.0  810.925276      412.971190   199.012395
+    96  12544.0  810.925276      412.546756   198.569388
-    97  12672.0  811.007961      412.097543   199.069228
+    97  12672.0  811.007961      412.097543   198.679085
 
     [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  31.142 seconds)
+   **Total running time of the script:** ( 3 minutes  33.253 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              3.276800
+    0    256.0   2.730667  ...   2.978909              2.978909
     1    384.0   7.372800  ...   7.899428              7.899428
     2    512.0  14.563555  ...  15.420235             15.420235
     3    640.0  22.260869  ...  24.380953             24.380953
     4    768.0  32.768000  ...  35.389441             34.028308
     5    896.0  39.025776  ...  40.140799             39.025776
     6   1024.0  49.932191  ...  53.773130             52.428801
-    7   1152.0  45.242181  ...  47.396572             47.396572
+    7   1152.0  45.242181  ...  48.161033             47.396572
     8   1280.0  51.200001  ...  57.690139             57.690139
     9   1408.0  64.138541  ...  68.147202             67.305878
-    10  1536.0  80.430545  ...  80.430545             78.643199
+    10  1536.0  80.430545  ...  81.355034             79.526831
-    11  1664.0  63.372618  ...  63.372618             62.492442
+    11  1664.0  62.929456  ...  63.372618             62.492442
-    12  1792.0  72.983276  ...  73.460287             59.467852
+    12  1792.0  72.983276  ...  72.983276             59.467852
-    13  1920.0  68.776119  ...  71.257735             71.257735
+    13  1920.0  69.120002  ...  71.626943             71.626943
-    14  2048.0  73.584279  ...  78.033565             77.314362
+    14  2048.0  73.908442  ...  78.398206             77.314362
-    15  2176.0  83.155572  ...  87.494120             85.998493
+    15  2176.0  83.500614  ...  87.494120             85.998493
-    16  2304.0  68.251065  ...  78.320893             77.558029
+    16  2304.0  68.251065  ...  77.810656             77.307030
-    17  2432.0  71.305746  ...  86.711310             86.179335
+    17  2432.0  71.305746  ...  86.711310             85.653855
-    18  2560.0  78.019048  ...  82.747477             81.715711
+    18  2560.0  77.833728  ...  82.539044             81.310171
-    19  2688.0  83.369354  ...  90.316801             89.254248
+    19  2688.0  83.737433  ...  90.532356             89.464755
-    20  2816.0  84.197315  ...  84.523664             84.035084
+    20  2816.0  83.873477  ...  84.687779             84.035084
-    21  2944.0  81.498008  ...  83.758038             82.237674
+    21  2944.0  82.509987  ...  83.899046             82.646820
-    22  3072.0  82.420822  ...  90.452244             88.060814
+    22  3072.0  81.825298  ...  89.877939             88.473602
-    23  3200.0  84.880639  ...  97.116842             95.665176
+    23  3200.0  84.432717  ...  96.896287             95.593730
-    24  3328.0  83.130825  ...  85.500351             85.703924
+    24  3328.0  83.130825  ...  85.857242             83.130825
-    25  3456.0  82.099354  ...  91.928814             86.596744
+    25  3456.0  82.519518  ...  89.084603             90.281712
-    26  3584.0  86.623693  ...  92.600816             95.960933
+    26  3584.0  84.111686  ...  92.315595             95.756542
-    27  3712.0  85.675250  ...  89.957089             87.860458
+    27  3712.0  85.970176  ...  89.755028             87.937800
-    28  3840.0  81.198237  ...  86.130841             90.205545
+    28  3840.0  81.138664  ...  89.839159             90.205545
-    29  3968.0  87.913500  ...  92.442373             87.976885
+    29  3968.0  86.051653  ...  92.442373             85.932350
-    30  4096.0  93.401342  ...  87.211002             85.543487
+    30  4096.0  94.453011  ...  87.267706             86.536250
 
     [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  34.968 seconds)
+   **Total running time of the script:** ( 6 minutes  27.642 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

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

@@ -41,33 +41,33 @@ Layer Normalization
     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
-    3    2560.0  694.237267  365.714281  518.481028
+    3    2560.0  694.237267  362.477870  512.000013
     4    3072.0  712.347810  378.092307  496.484863
-    5    3584.0  725.873439  384.859062  451.527536
+    5    3584.0  725.873439  384.859062  448.000001
     6    4096.0  728.177767  381.023256  455.111095
-    7    4608.0  670.254540  394.267384  421.302872
+    7    4608.0  670.254540  394.267384  426.173427
-    8    5120.0  688.403381  397.669909  424.455959
+    8    5120.0  688.403381  397.669909  420.102563
-    9    5632.0  698.542675  396.969169  411.470331
+    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  686.754468  396.844306  387.459443
+    12   7168.0  690.891575  396.844306  386.154893
-    13   7680.0  682.666656  393.846167  386.415087
+    13   7680.0  678.895043  392.587863  386.415087
-    14   8192.0  636.271854  393.609605  371.308771
+    14   8192.0  633.198054  393.609605  371.308771
-    15   8704.0  627.315309  389.005597  381.545190
+    15   8704.0  627.315309  389.005597  380.502740
-    16   9216.0  606.814809  407.337026  383.999986
+    16   9216.0  606.814809  407.337026  383.002605
-    17   9728.0  587.350922  409.599987  383.369452
+    17   9728.0  587.350922  409.599987  382.427505
     18  10240.0  564.965524  408.578556  382.803739
-    19  10752.0  546.133312  412.546760  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  410.492372  377.587162
+    21  11776.0  520.486200  409.599991  377.587162
-    22  12288.0  514.680630  414.784810  383.251457
+    22  12288.0  513.336807  413.911572  383.251457
     23  12800.0  504.433489  410.420828  376.470582
-    24  13312.0  494.180982  405.699062  376.976995
+    24  13312.0  494.180982  405.699062  376.310952
-    25  13824.0  481.882350  411.888257  379.389355
+    25  13824.0  481.882350  411.122660  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  376.225175
+    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  37.668 seconds)
+   **Total running time of the script:** ( 5 minutes  33.977 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

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

@@ -385,7 +385,7 @@ 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  0.071 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_06-fused-attention.py:

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

@@ -5,18 +5,18 @@
 
 Computation times
 =================
-**17:30.791** total execution time for **getting-started_tutorials** files:
+**17:23.743** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:34.968 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:27.642 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:37.668 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:33.977 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:31.142 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:33.253 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:46.918 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:48.779 | 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``)             | 00:00.071 | 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 |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -327,22 +327,22 @@ for different problem sizes.</p>
 0        4096.0    9.600000    9.600000
 1        8192.0   19.200000   19.200000
 2       16384.0   38.400001   38.400001
-3       32768.0   63.999998   63.999998
+3       32768.0   76.800002   76.800002
 4       65536.0  127.999995  127.999995
 5      131072.0  219.428568  219.428568
 6      262144.0  341.333321  384.000001
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
-9     2097152.0  722.823517  702.171410
+9     2097152.0  722.823517  722.823517
 10    4194304.0  780.190482  780.190482
 11    8388608.0  812.429770  812.429770
 12   16777216.0  833.084721  833.084721
-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  46.918 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  48.779 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      512.000001   190.511628
+0     256.0  546.133347      512.000001   190.511628
 1     384.0  614.400016      585.142862   153.600004
 2     512.0  655.360017      585.142849   154.566038
 3     640.0  706.206879      640.000002   158.759699
-4     768.0  722.823517      664.216187   162.754967
+4     768.0  722.823517      664.216187   161.684218
 ..      ...         ...             ...          ...
-93  12160.0  812.359066      406.179533   198.834951
+93  12160.0  812.359066      406.179533   198.328233
-94  12288.0  812.429770      415.881552   199.096718
+94  12288.0  812.429770      415.222812   198.694297
-95  12416.0  812.498981      412.149375   198.755369
+95  12416.0  812.498981      411.722274   198.358474
-96  12544.0  810.925276      412.971190   199.012395
+96  12544.0  810.925276      412.546756   198.569388
-97  12672.0  811.007961      412.097543   199.069228
+97  12672.0  811.007961      412.097543   198.679085
 
 [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  31.142 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  33.253 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              3.276800
+0    256.0   2.730667  ...   2.978909              2.978909
 1    384.0   7.372800  ...   7.899428              7.899428
 2    512.0  14.563555  ...  15.420235             15.420235
 3    640.0  22.260869  ...  24.380953             24.380953
 4    768.0  32.768000  ...  35.389441             34.028308
 5    896.0  39.025776  ...  40.140799             39.025776
 6   1024.0  49.932191  ...  53.773130             52.428801
-7   1152.0  45.242181  ...  47.396572             47.396572
+7   1152.0  45.242181  ...  48.161033             47.396572
 8   1280.0  51.200001  ...  57.690139             57.690139
 9   1408.0  64.138541  ...  68.147202             67.305878
-10  1536.0  80.430545  ...  80.430545             78.643199
+10  1536.0  80.430545  ...  81.355034             79.526831
-11  1664.0  63.372618  ...  63.372618             62.492442
+11  1664.0  62.929456  ...  63.372618             62.492442
-12  1792.0  72.983276  ...  73.460287             59.467852
+12  1792.0  72.983276  ...  72.983276             59.467852
-13  1920.0  68.776119  ...  71.257735             71.257735
+13  1920.0  69.120002  ...  71.626943             71.626943
-14  2048.0  73.584279  ...  78.033565             77.314362
+14  2048.0  73.908442  ...  78.398206             77.314362
-15  2176.0  83.155572  ...  87.494120             85.998493
+15  2176.0  83.500614  ...  87.494120             85.998493
-16  2304.0  68.251065  ...  78.320893             77.558029
+16  2304.0  68.251065  ...  77.810656             77.307030
-17  2432.0  71.305746  ...  86.711310             86.179335
+17  2432.0  71.305746  ...  86.711310             85.653855
-18  2560.0  78.019048  ...  82.747477             81.715711
+18  2560.0  77.833728  ...  82.539044             81.310171
-19  2688.0  83.369354  ...  90.316801             89.254248
+19  2688.0  83.737433  ...  90.532356             89.464755
-20  2816.0  84.197315  ...  84.523664             84.035084
+20  2816.0  83.873477  ...  84.687779             84.035084
-21  2944.0  81.498008  ...  83.758038             82.237674
+21  2944.0  82.509987  ...  83.899046             82.646820
-22  3072.0  82.420822  ...  90.452244             88.060814
+22  3072.0  81.825298  ...  89.877939             88.473602
-23  3200.0  84.880639  ...  97.116842             95.665176
+23  3200.0  84.432717  ...  96.896287             95.593730
-24  3328.0  83.130825  ...  85.500351             85.703924
+24  3328.0  83.130825  ...  85.857242             83.130825
-25  3456.0  82.099354  ...  91.928814             86.596744
+25  3456.0  82.519518  ...  89.084603             90.281712
-26  3584.0  86.623693  ...  92.600816             95.960933
+26  3584.0  84.111686  ...  92.315595             95.756542
-27  3712.0  85.675250  ...  89.957089             87.860458
+27  3712.0  85.970176  ...  89.755028             87.937800
-28  3840.0  81.198237  ...  86.130841             90.205545
+28  3840.0  81.138664  ...  89.839159             90.205545
-29  3968.0  87.913500  ...  92.442373             87.976885
+29  3968.0  86.051653  ...  92.442373             85.932350
-30  4096.0  93.401342  ...  87.211002             85.543487
+30  4096.0  94.453011  ...  87.267706             86.536250
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  34.968 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  27.642 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

@@ -199,33 +199,33 @@ 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  668.734716  334.367358  520.126988
-3    2560.0  694.237267  365.714281  518.481028
+3    2560.0  694.237267  362.477870  512.000013
 4    3072.0  712.347810  378.092307  496.484863
-5    3584.0  725.873439  384.859062  451.527536
+5    3584.0  725.873439  384.859062  448.000001
 6    4096.0  728.177767  381.023256  455.111095
-7    4608.0  670.254540  394.267384  421.302872
+7    4608.0  670.254540  394.267384  426.173427
-8    5120.0  688.403381  397.669909  424.455959
+8    5120.0  688.403381  397.669909  420.102563
-9    5632.0  698.542675  396.969169  411.470331
+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  686.754468  396.844306  387.459443
+12   7168.0  690.891575  396.844306  386.154893
-13   7680.0  682.666656  393.846167  386.415087
+13   7680.0  678.895043  392.587863  386.415087
-14   8192.0  636.271854  393.609605  371.308771
+14   8192.0  633.198054  393.609605  371.308771
-15   8704.0  627.315309  389.005597  381.545190
+15   8704.0  627.315309  389.005597  380.502740
-16   9216.0  606.814809  407.337026  383.999986
+16   9216.0  606.814809  407.337026  383.002605
-17   9728.0  587.350922  409.599987  383.369452
+17   9728.0  587.350922  409.599987  382.427505
 18  10240.0  564.965524  408.578556  382.803739
-19  10752.0  546.133312  412.546760  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  410.492372  377.587162
+21  11776.0  520.486200  409.599991  377.587162
-22  12288.0  514.680630  414.784810  383.251457
+22  12288.0  513.336807  413.911572  383.251457
 23  12800.0  504.433489  410.420828  376.470582
-24  13312.0  494.180982  405.699062  376.976995
+24  13312.0  494.180982  405.699062  376.310952
-25  13824.0  481.882350  411.888257  379.389355
+25  13824.0  481.882350  411.122660  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  376.225175
+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  37.668 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  33.977 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

@@ -543,7 +543,7 @@ 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  0.071 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/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>17:30.791</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>17:23.743</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>06:34.968</p></td>
+<td><p>06:27.642</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>05:37.668</p></td>
+<td><p>05:33.977</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>03:31.142</p></td>
+<td><p>03:33.253</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>01:46.918</p></td>
+<td><p>01:48.779</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>00:00.071</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>

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: 9d9a3e500aeaa03f168669637d5e8d1c
+config: 7e982019190a921a53142a76627d87ef
 tags: 645f666f9bcd5a90fca523b33c5a78b7