[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: dcb51d10379790b23b9f305eb4789868
+config: 2669b1fb9e287aa7444c99f28247942d
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -238,14 +238,14 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     3       32768.0   63.999998   63.999998
     4       65536.0  127.999995  127.999995
     5      131072.0  219.428568  219.428568
-    6      262144.0  341.333321  341.333321
+    6      262144.0  341.333321  384.000001
     7      524288.0  472.615390  472.615390
     8     1048576.0  614.400016  614.400016
-    9     2097152.0  702.171410  702.171410
+    9     2097152.0  722.823517  722.823517
-    10    4194304.0  780.190482  768.000002
+    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  842.004273
+    13   33554432.0  842.004273  843.811163
     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  48.554 seconds)
+   **Total running time of the script:** ( 1 minutes  39.155 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   186.181817
+    0     256.0  512.000001      546.133347   190.511628
     1     384.0  438.857137      558.545450   151.703707
-    2     512.0  468.114273      585.142849   154.566038
+    2     512.0  481.882344      606.814814   154.566038
     3     640.0  465.454542      640.000002   158.759699
-    4     768.0  472.615390      664.216187   163.839992
+    4     768.0  463.698115      664.216187   163.839992
     ..      ...         ...             ...          ...
-    93  12160.0  478.034381      405.333344   198.834951
+    93  12160.0  479.211815      405.333344   199.038365
-    94  12288.0  484.256150      415.222812   199.096718
+    94  12288.0  484.853264      415.222812   199.197579
-    95  12416.0  461.454135      411.296057   198.755369
+    95  12416.0  460.384708      412.149375   198.954424
-    96  12544.0  458.228323      412.971190   198.815254
+    96  12544.0  457.705824      412.546756   199.012395
-    97  12672.0  458.196617      411.679167   198.971549
+    97  12672.0  457.679461      411.679167   199.167004
 
     [98 rows x 4 columns]
 
@@ -306,7 +306,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  10.849 seconds)
+   **Total running time of the script:** ( 3 minutes  8.135 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -458,37 +458,37 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
 
     matmul-performance:
              M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
-    0    256.0   2.730667  ...   2.978909              2.978909
+    0    256.0   2.730667  ...   3.276800              3.276800
-    1    384.0   7.372800  ...   8.507077              8.507077
+    1    384.0   7.372800  ...   7.899428              7.899428
-    2    512.0  14.563555  ...  15.420235             15.420235
+    2    512.0  14.563555  ...  16.384000             16.384000
     3    640.0  22.260869  ...  24.380953             24.380953
-    4    768.0  32.768000  ...  34.028308             34.028308
+    4    768.0  32.768000  ...  35.389441             34.028308
     5    896.0  37.971025  ...  40.140799             40.140799
-    6   1024.0  49.932191  ...  53.773130             52.428801
+    6   1024.0  49.932191  ...  53.773130             53.773130
     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
+    9   1408.0  64.138541  ...  69.009825             68.147202
     10  1536.0  79.526831  ...  79.526831             79.526831
-    11  1664.0  62.929456  ...  62.929456             62.492442
+    11  1664.0  63.372618  ...  63.372618             62.929456
-    12  1792.0  72.512412  ...  63.142831             62.790080
+    12  1792.0  72.983276  ...  63.499573             63.142831
-    13  1920.0  69.120002  ...  71.626943             70.892307
+    13  1920.0  69.467336  ...  71.257735             71.257735
-    14  2048.0  73.584279  ...  78.033565             77.672296
+    14  2048.0  73.262953  ...  78.033565             77.672296
     15  2176.0  83.155572  ...  87.115360             86.739860
     16  2304.0  68.251065  ...  78.064941             77.558029
-    17  2432.0  71.125224  ...  75.522751             75.320281
+    17  2432.0  71.305746  ...  75.522751             75.320281
-    18  2560.0  77.833728  ...  82.331658             81.920002
+    18  2560.0  77.833728  ...  82.331658             82.125311
-    19  2688.0  83.645109  ...  90.102270             90.102270
+    19  2688.0  83.552988  ...  90.748936             90.316801
-    20  2816.0  80.026067  ...  83.712490             81.981598
+    20  2816.0  84.035084  ...  83.873477             84.035084
-    21  2944.0  82.509987  ...  82.852924             82.646820
+    21  2944.0  82.784108  ...  84.324925             84.040530
-    22  3072.0  82.540970  ...  86.845249             89.593522
+    22  3072.0  82.540970  ...  89.170242             89.030036
-    23  3200.0  84.993363  ...  96.240602             96.096095
+    23  3200.0  84.768213  ...  95.096582             95.380032
-    24  3328.0  83.034941  ...  83.905938             82.843841
+    24  3328.0  83.808259  ...  85.500351             86.424125
-    25  3456.0  81.849303  ...  89.679166             90.382926
+    25  3456.0  82.604067  ...  92.033756             91.719645
-    26  3584.0  85.797134  ...  93.467144             98.483450
+    26  3584.0  87.466332  ...  92.696281             96.372338
-    27  3712.0  85.748791  ...  86.754095             88.170647
+    27  3712.0  86.267139  ...  85.970176             88.248537
-    28  3840.0  81.798814  ...  87.841141             91.473945
+    28  3840.0  82.716526  ...  86.400002             91.322872
-    29  3968.0  85.871877  ...  92.582651             84.738843
+    29  3968.0  85.871877  ...  92.163097             87.472354
-    30  4096.0  94.386588  ...  84.894196             82.722796
+    30  4096.0  93.924229  ...  94.055868             87.097813
 
     [31 rows x 5 columns]
 
@@ -498,7 +498,7 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 6 minutes  44.900 seconds)
+   **Total running time of the script:** ( 6 minutes  0.518 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  0.325 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

@@ -38,36 +38,36 @@ Layer Normalization
 
     layer-norm-backward:
               N      Triton       Torch        Apex
-    0    1024.0  114.306981   98.698793  315.076934
+    0    1024.0  114.306981   97.912354  303.407414
-    1    1536.0  118.153850  132.604320  341.333333
+    1    1536.0  118.153850  134.540150  341.333333
-    2    2048.0  125.068704  159.584422  332.108094
+    2    2048.0  125.068704  161.154101  334.367350
-    3    2560.0  119.300966  180.705883  332.108113
+    3    2560.0  119.766080  181.238943  330.322572
-    4    3072.0  123.912607  191.005181  320.556515
+    4    3072.0  124.121216  192.501302  323.368415
-    5    3584.0  127.809806  207.267476  310.527060
+    5    3584.0  127.242599  208.271186  311.652167
-    6    4096.0  130.723400  220.907859  296.990947
+    6    4096.0  130.549806  220.907859  296.990947
-    7    4608.0  105.325718  232.336141  287.999990
+    7    4608.0  105.526723  232.825259  287.251954
-    8    5120.0  108.647215  241.414550  283.787523
+    8    5120.0  108.743364  242.366855  284.444444
-    9    5632.0  109.714290  241.371422  288.204696
+    9    5632.0  109.625308  243.107920  290.060087
-    10   6144.0  112.133840  249.502530  287.438593
+    10   6144.0  112.133840  248.661056  286.879370
-    11   6656.0  112.733948  254.775119  285.257135
+    11   6656.0  112.733948  256.000009  285.767438
-    12   7168.0  114.994654  257.147993  281.098038
+    12   7168.0  114.917836  260.260201  284.821192
-    13   7680.0  115.128047  264.068761  281.834874
+    13   7680.0  115.128047  262.938666  280.121579
-    14   8192.0  115.856217  267.493874  282.889211
+    14   8192.0  115.856217  266.767970  284.526763
-    15   8704.0   94.054934  264.091015  282.673891
+    15   8704.0   94.182151  267.815384  285.377055
-    16   9216.0   96.755908  271.391419  287.625496
+    16   9216.0   96.713601  271.724806  287.999990
-    17   9728.0   97.768843  280.615388  288.950501
+    17   9728.0   97.687028  280.615388  290.027323
-    18  10240.0  100.105904  285.104413  289.129408
+    18  10240.0  100.065144  286.433562  290.153487
-    19  10752.0  101.036809  246.464170  290.594591
+    19  10752.0  101.115983  246.935876  290.594591
-    20  11264.0  102.945926  245.536784  286.676558
+    20  11264.0  103.024392  245.536784  286.980888
-    21  11776.0  103.601171  249.447482  288.981596
+    21  11776.0  103.373808  249.667843  288.981596
-    22  12288.0  106.159829  254.673582  294.911986
+    22  12288.0  106.083454  254.673582  294.617366
-    23  12800.0  106.187352  253.884294  289.811310
+    23  12800.0  106.004143  254.094291  288.180121
-    24  13312.0  107.463167  251.962147  289.129403
+    24  13312.0  107.067028  253.260416  290.443638
-    25  13824.0  107.544896  256.792581  292.313649
+    25  13824.0  107.440415  257.390218  292.056329
-    26  14336.0  109.435116  254.673567  287.198654
+    26  14336.0  109.296061  255.051144  286.959121
-    27  14848.0  109.276912  255.266469  289.481735
+    27  14848.0  109.143034  257.665934  289.952797
-    28  15360.0  110.669469  260.338991  290.496454
+    28  15360.0  110.802526  257.970599  288.000007
-    29  15872.0  110.863792  263.071829  291.898841
+    29  15872.0  110.702706  261.806182  290.341468
 
 
 
@@ -339,7 +339,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  2.489 seconds)
+   **Total running time of the script:** ( 2 minutes  0.332 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

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

@@ -5,16 +5,16 @@
 
 Computation times
 =================
-**13:47.116** total execution time for **getting-started_tutorials** files:
+**12:48.152** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:44.900 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:00.518 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:10.849 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:08.135 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:02.489 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:00.332 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:48.554 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:39.155 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.325 | 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

@@ -328,19 +328,19 @@ for different problem sizes.</p>
 3       32768.0   63.999998   63.999998
 4       65536.0  127.999995  127.999995
 5      131072.0  219.428568  219.428568
-6      262144.0  341.333321  341.333321
+6      262144.0  341.333321  384.000001
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
-9     2097152.0  702.171410  702.171410
+9     2097152.0  722.823517  722.823517
-10    4194304.0  780.190482  768.000002
+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  842.004273
+13   33554432.0  842.004273  843.811163
 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  48.554 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  39.155 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-01-vector-add-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/62d97d49a32414049819dd8bb8378080/01-vector-add.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">01-vector-add.py</span></code></a></p>

master/getting-started/tutorials/02-fused-softmax.html

@@ -369,17 +369,17 @@ We will then compare its performance against (1) <code class="code docutils lite
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>softmax-performance:
           N      Triton  Torch (native)  Torch (jit)
-0     256.0  512.000001      546.133347   186.181817
+0     256.0  512.000001      546.133347   190.511628
 1     384.0  438.857137      558.545450   151.703707
-2     512.0  468.114273      585.142849   154.566038
+2     512.0  481.882344      606.814814   154.566038
 3     640.0  465.454542      640.000002   158.759699
-4     768.0  472.615390      664.216187   163.839992
+4     768.0  463.698115      664.216187   163.839992
 ..      ...         ...             ...          ...
-93  12160.0  478.034381      405.333344   198.834951
+93  12160.0  479.211815      405.333344   199.038365
-94  12288.0  484.256150      415.222812   199.096718
+94  12288.0  484.853264      415.222812   199.197579
-95  12416.0  461.454135      411.296057   198.755369
+95  12416.0  460.384708      412.149375   198.954424
-96  12544.0  458.228323      412.971190   198.815254
+96  12544.0  457.705824      412.546756   199.012395
-97  12672.0  458.196617      411.679167   198.971549
+97  12672.0  457.679461      411.679167   199.167004
 
 [98 rows x 4 columns]
 </pre></div>
@@ -392,7 +392,7 @@ We will then compare its performance against (1) <code class="code docutils lite
 Note however that the PyTorch <cite>softmax</cite> operation is more general and will works on tensors of any shape.</p></li>
 </ul>
 </div></blockquote>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  10.849 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  8.135 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-02-fused-softmax-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/d91442ac2982c4e0cc3ab0f43534afbc/02-fused-softmax.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">02-fused-softmax.py</span></code></a></p>

master/getting-started/tutorials/03-matrix-multiplication.html

@@ -564,42 +564,42 @@ torch_output=tensor([[  1.1045, -36.9688,  31.4688,  ..., -11.3906,  24.4531, -3
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>matmul-performance:
          M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
-0    256.0   2.730667  ...   2.978909              2.978909
+0    256.0   2.730667  ...   3.276800              3.276800
-1    384.0   7.372800  ...   8.507077              8.507077
+1    384.0   7.372800  ...   7.899428              7.899428
-2    512.0  14.563555  ...  15.420235             15.420235
+2    512.0  14.563555  ...  16.384000             16.384000
 3    640.0  22.260869  ...  24.380953             24.380953
-4    768.0  32.768000  ...  34.028308             34.028308
+4    768.0  32.768000  ...  35.389441             34.028308
 5    896.0  37.971025  ...  40.140799             40.140799
-6   1024.0  49.932191  ...  53.773130             52.428801
+6   1024.0  49.932191  ...  53.773130             53.773130
 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
+9   1408.0  64.138541  ...  69.009825             68.147202
 10  1536.0  79.526831  ...  79.526831             79.526831
-11  1664.0  62.929456  ...  62.929456             62.492442
+11  1664.0  63.372618  ...  63.372618             62.929456
-12  1792.0  72.512412  ...  63.142831             62.790080
+12  1792.0  72.983276  ...  63.499573             63.142831
-13  1920.0  69.120002  ...  71.626943             70.892307
+13  1920.0  69.467336  ...  71.257735             71.257735
-14  2048.0  73.584279  ...  78.033565             77.672296
+14  2048.0  73.262953  ...  78.033565             77.672296
 15  2176.0  83.155572  ...  87.115360             86.739860
 16  2304.0  68.251065  ...  78.064941             77.558029
-17  2432.0  71.125224  ...  75.522751             75.320281
+17  2432.0  71.305746  ...  75.522751             75.320281
-18  2560.0  77.833728  ...  82.331658             81.920002
+18  2560.0  77.833728  ...  82.331658             82.125311
-19  2688.0  83.645109  ...  90.102270             90.102270
+19  2688.0  83.552988  ...  90.748936             90.316801
-20  2816.0  80.026067  ...  83.712490             81.981598
+20  2816.0  84.035084  ...  83.873477             84.035084
-21  2944.0  82.509987  ...  82.852924             82.646820
+21  2944.0  82.784108  ...  84.324925             84.040530
-22  3072.0  82.540970  ...  86.845249             89.593522
+22  3072.0  82.540970  ...  89.170242             89.030036
-23  3200.0  84.993363  ...  96.240602             96.096095
+23  3200.0  84.768213  ...  95.096582             95.380032
-24  3328.0  83.034941  ...  83.905938             82.843841
+24  3328.0  83.808259  ...  85.500351             86.424125
-25  3456.0  81.849303  ...  89.679166             90.382926
+25  3456.0  82.604067  ...  92.033756             91.719645
-26  3584.0  85.797134  ...  93.467144             98.483450
+26  3584.0  87.466332  ...  92.696281             96.372338
-27  3712.0  85.748791  ...  86.754095             88.170647
+27  3712.0  86.267139  ...  85.970176             88.248537
-28  3840.0  81.798814  ...  87.841141             91.473945
+28  3840.0  82.716526  ...  86.400002             91.322872
-29  3968.0  85.871877  ...  92.582651             84.738843
+29  3968.0  85.871877  ...  92.163097             87.472354
-30  4096.0  94.386588  ...  84.894196             82.722796
+30  4096.0  93.924229  ...  94.055868             87.097813
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  44.900 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  0.518 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-03-matrix-multiplication-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/d5fee5b55a64e47f1b5724ec39adf171/03-matrix-multiplication.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">03-matrix-multiplication.py</span></code></a></p>

master/getting-started/tutorials/04-low-memory-dropout.html

@@ -372,7 +372,7 @@ to explore the <cite>triton/language/random</cite> folder!</p>
 <dd><p>Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting”, JMLR 2014</p>
 </dd>
 </dl>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.325 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

@@ -194,36 +194,36 @@ to download the full example code</p>
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>layer-norm-backward:
           N      Triton       Torch        Apex
-0    1024.0  114.306981   98.698793  315.076934
+0    1024.0  114.306981   97.912354  303.407414
-1    1536.0  118.153850  132.604320  341.333333
+1    1536.0  118.153850  134.540150  341.333333
-2    2048.0  125.068704  159.584422  332.108094
+2    2048.0  125.068704  161.154101  334.367350
-3    2560.0  119.300966  180.705883  332.108113
+3    2560.0  119.766080  181.238943  330.322572
-4    3072.0  123.912607  191.005181  320.556515
+4    3072.0  124.121216  192.501302  323.368415
-5    3584.0  127.809806  207.267476  310.527060
+5    3584.0  127.242599  208.271186  311.652167
-6    4096.0  130.723400  220.907859  296.990947
+6    4096.0  130.549806  220.907859  296.990947
-7    4608.0  105.325718  232.336141  287.999990
+7    4608.0  105.526723  232.825259  287.251954
-8    5120.0  108.647215  241.414550  283.787523
+8    5120.0  108.743364  242.366855  284.444444
-9    5632.0  109.714290  241.371422  288.204696
+9    5632.0  109.625308  243.107920  290.060087
-10   6144.0  112.133840  249.502530  287.438593
+10   6144.0  112.133840  248.661056  286.879370
-11   6656.0  112.733948  254.775119  285.257135
+11   6656.0  112.733948  256.000009  285.767438
-12   7168.0  114.994654  257.147993  281.098038
+12   7168.0  114.917836  260.260201  284.821192
-13   7680.0  115.128047  264.068761  281.834874
+13   7680.0  115.128047  262.938666  280.121579
-14   8192.0  115.856217  267.493874  282.889211
+14   8192.0  115.856217  266.767970  284.526763
-15   8704.0   94.054934  264.091015  282.673891
+15   8704.0   94.182151  267.815384  285.377055
-16   9216.0   96.755908  271.391419  287.625496
+16   9216.0   96.713601  271.724806  287.999990
-17   9728.0   97.768843  280.615388  288.950501
+17   9728.0   97.687028  280.615388  290.027323
-18  10240.0  100.105904  285.104413  289.129408
+18  10240.0  100.065144  286.433562  290.153487
-19  10752.0  101.036809  246.464170  290.594591
+19  10752.0  101.115983  246.935876  290.594591
-20  11264.0  102.945926  245.536784  286.676558
+20  11264.0  103.024392  245.536784  286.980888
-21  11776.0  103.601171  249.447482  288.981596
+21  11776.0  103.373808  249.667843  288.981596
-22  12288.0  106.159829  254.673582  294.911986
+22  12288.0  106.083454  254.673582  294.617366
-23  12800.0  106.187352  253.884294  289.811310
+23  12800.0  106.004143  254.094291  288.180121
-24  13312.0  107.463167  251.962147  289.129403
+24  13312.0  107.067028  253.260416  290.443638
-25  13824.0  107.544896  256.792581  292.313649
+25  13824.0  107.440415  257.390218  292.056329
-26  14336.0  109.435116  254.673567  287.198654
+26  14336.0  109.296061  255.051144  286.959121
-27  14848.0  109.276912  255.266469  289.481735
+27  14848.0  109.143034  257.665934  289.952797
-28  15360.0  110.669469  260.338991  290.496454
+28  15360.0  110.802526  257.970599  288.000007
-29  15872.0  110.863792  263.071829  291.898841
+29  15872.0  110.702706  261.806182  290.341468
 </pre></div>
 </div>
 <div class="line-block">
@@ -487,7 +487,7 @@ to download the full example code</p>
 <span class="n">bench_layer_norm</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">save_path</span><span class="o">=</span><span class="s1">&#39;.&#39;</span><span class="p">,</span> <span class="n">print_data</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  2.489 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  0.332 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-05-layer-norm-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/935c0dd0fbeb4b2e69588471cbb2d4b2/05-layer-norm.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">05-layer-norm.py</span></code></a></p>

master/getting-started/tutorials/sg_execution_times.html

@@ -174,7 +174,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-getting-started-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:47.116</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>12:48.152</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>06:44.900</p></td>
+<td><p>06:00.518</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="02-fused-softmax.html#sphx-glr-getting-started-tutorials-02-fused-softmax-py"><span class="std std-ref">Fused Softmax</span></a> (<code class="docutils literal notranslate"><span class="pre">02-fused-softmax.py</span></code>)</p></td>
-<td><p>03:10.849</p></td>
+<td><p>03:08.135</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="05-layer-norm.html#sphx-glr-getting-started-tutorials-05-layer-norm-py"><span class="std std-ref">Layer Normalization</span></a> (<code class="docutils literal notranslate"><span class="pre">05-layer-norm.py</span></code>)</p></td>
-<td><p>02:02.489</p></td>
+<td><p>02:00.332</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>01:48.554</p></td>
+<td><p>01:39.155</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="04-low-memory-dropout.html#sphx-glr-getting-started-tutorials-04-low-memory-dropout-py"><span class="std std-ref">Low-Memory Dropout</span></a> (<code class="docutils literal notranslate"><span class="pre">04-low-memory-dropout.py</span></code>)</p></td>
-<td><p>00:00.325</p></td>
+<td><p>00:00.012</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>

v1.1.2/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 859316008f2f6719727d4fb3b970c7e2
+config: 0f666e711caacc26933f91d5b974ab34
 tags: 645f666f9bcd5a90fca523b33c5a78b7