[GH-PAGES] Updated website

triton-lang · Jul 6, 2024 · a40b0e3 · a40b0e3
1 parent 1927a7c
commit a40b0e3
Show file tree

Hide file tree

Showing 52 changed files with 425 additions and 425 deletions.
diff --git a/main/.doctrees/environment.pickle b/main/.doctrees/environment.pickle
diff --git a/main/.doctrees/getting-started/tutorials/01-vector-add.doctree b/main/.doctrees/getting-started/tutorials/01-vector-add.doctree
diff --git a/main/.doctrees/getting-started/tutorials/02-fused-softmax.doctree b/main/.doctrees/getting-started/tutorials/02-fused-softmax.doctree
diff --git a/main/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree b/main/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree
diff --git a/main/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree b/main/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree
diff --git a/main/.doctrees/getting-started/tutorials/05-layer-norm.doctree b/main/.doctrees/getting-started/tutorials/05-layer-norm.doctree
diff --git a/main/.doctrees/getting-started/tutorials/06-fused-attention.doctree b/main/.doctrees/getting-started/tutorials/06-fused-attention.doctree
diff --git a/main/.doctrees/getting-started/tutorials/07-extern-functions.doctree b/main/.doctrees/getting-started/tutorials/07-extern-functions.doctree
diff --git a/main/.doctrees/getting-started/tutorials/08-grouped-gemm.doctree b/main/.doctrees/getting-started/tutorials/08-grouped-gemm.doctree
diff --git a/main/.doctrees/getting-started/tutorials/09-persistent-matmul.doctree b/main/.doctrees/getting-started/tutorials/09-persistent-matmul.doctree
diff --git a/main/.doctrees/getting-started/tutorials/sg_execution_times.doctree b/main/.doctrees/getting-started/tutorials/sg_execution_times.doctree
diff --git a/main/.doctrees/sg_execution_times.doctree b/main/.doctrees/sg_execution_times.doctree
diff --git a/main/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip b/main/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip
diff --git a/main/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip b/main/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip
diff --git a/main/_images/sphx_glr_01-vector-add_001.png b/main/_images/sphx_glr_01-vector-add_001.png
diff --git a/main/_images/sphx_glr_01-vector-add_thumb.png b/main/_images/sphx_glr_01-vector-add_thumb.png
diff --git a/main/_images/sphx_glr_02-fused-softmax_001.png b/main/_images/sphx_glr_02-fused-softmax_001.png
diff --git a/main/_images/sphx_glr_02-fused-softmax_thumb.png b/main/_images/sphx_glr_02-fused-softmax_thumb.png
diff --git a/main/_images/sphx_glr_03-matrix-multiplication_001.png b/main/_images/sphx_glr_03-matrix-multiplication_001.png
diff --git a/main/_images/sphx_glr_03-matrix-multiplication_002.png b/main/_images/sphx_glr_03-matrix-multiplication_002.png
diff --git a/main/_images/sphx_glr_03-matrix-multiplication_thumb.png b/main/_images/sphx_glr_03-matrix-multiplication_thumb.png
diff --git a/main/_images/sphx_glr_05-layer-norm_001.png b/main/_images/sphx_glr_05-layer-norm_001.png
diff --git a/main/_images/sphx_glr_05-layer-norm_thumb.png b/main/_images/sphx_glr_05-layer-norm_thumb.png
diff --git a/main/_images/sphx_glr_06-fused-attention_001.png b/main/_images/sphx_glr_06-fused-attention_001.png
diff --git a/main/_images/sphx_glr_06-fused-attention_002.png b/main/_images/sphx_glr_06-fused-attention_002.png
diff --git a/main/_images/sphx_glr_06-fused-attention_003.png b/main/_images/sphx_glr_06-fused-attention_003.png
diff --git a/main/_images/sphx_glr_06-fused-attention_thumb.png b/main/_images/sphx_glr_06-fused-attention_thumb.png
diff --git a/main/_images/sphx_glr_08-grouped-gemm_001.png b/main/_images/sphx_glr_08-grouped-gemm_001.png
diff --git a/main/_images/sphx_glr_08-grouped-gemm_thumb.png b/main/_images/sphx_glr_08-grouped-gemm_thumb.png
diff --git a/main/_sources/getting-started/tutorials/01-vector-add.rst.txt b/main/_sources/getting-started/tutorials/01-vector-add.rst.txt
@@ -239,10 +239,10 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     6      262144.0   384.000001   384.000001
     7      524288.0   614.400016   614.400016
     8     1048576.0   819.200021   819.200021
-    9     2097152.0  1068.521715  1023.999964
-    10    4194304.0  1228.800031  1228.800031
-    11    8388608.0  1424.695621  1404.342820
-    12   16777216.0  1560.380965  1548.094408
+    9     2097152.0  1023.999964  1023.999964
+    10    4194304.0  1228.800031  1260.307736
+    11    8388608.0  1424.695621  1424.695621
+    12   16777216.0  1560.380965  1560.380965
     13   33554432.0  1631.601649  1624.859540
     14   67108864.0  1669.706983  1662.646960
     15  134217728.0  1684.008546  1678.616907
@@ -253,7 +253,7 @@ 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:** (0 minutes 8.381 seconds)
+   **Total running time of the script:** (0 minutes 6.989 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

diff --git a/main/_sources/getting-started/tutorials/02-fused-softmax.rst.txt b/main/_sources/getting-started/tutorials/02-fused-softmax.rst.txt
@@ -303,104 +303,104 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
 
     softmax-performance:
               N       Triton        Torch
-    0     256.0   470.558695   686.886310
-    1     384.0   607.494214   803.171817
-    2     512.0   746.730629   923.498288
-    3     640.0   785.500895   957.464398
-    4     768.0   871.706342  1014.637773
-    5     896.0   934.083133  1074.320476
-    6    1024.0   995.927398  1110.276581
-    7    1152.0  1106.657711   610.462891
-    8    1280.0  1149.284748   668.572192
-    9    1408.0  1152.105060   724.012869
-    10   1536.0  1192.866856   778.268149
-    11   1664.0  1218.737417   815.281895
-    12   1792.0  1231.247559   854.239903
-    13   1920.0  1246.901010   907.284601
-    14   2048.0  1268.051491   953.763381
-    15   2176.0  1262.585646   976.703904
-    16   2304.0  1268.741762  1011.088050
-    17   2432.0  1299.137815  1052.134430
-    18   2560.0  1297.708162  1081.875577
-    19   2688.0  1308.458534  1099.511116
-    20   2816.0  1319.850920  1130.606932
-    21   2944.0  1327.003068  1162.583354
-    22   3072.0  1352.893306  1185.499824
-    23   3200.0  1345.314837  1190.432792
-    24   3328.0  1355.777511  1220.162226
-    25   3456.0  1375.290627  1247.909395
-    26   3584.0  1373.092922  1261.302738
-    27   3712.0  1382.233486  1269.606293
-    28   3840.0  1383.535869  1301.771090
-    29   3968.0  1390.721221  1310.876901
-    30   4096.0  1394.723434  1327.045013
-    31   4224.0  1330.975956  1163.816265
-    32   4352.0  1338.383198  1172.068872
-    33   4480.0  1349.789952  1185.261173
-    34   4608.0  1362.529862  1192.658713
-    35   4736.0  1354.922801  1194.904546
-    36   4864.0  1380.394439  1219.083715
-    37   4992.0  1368.600928  1237.443439
-    38   5120.0  1372.767584  1248.491954
-    39   5248.0  1377.610270  1256.961642
-    40   5376.0  1375.351942  1288.253600
-    41   5504.0  1384.055005  1298.703316
-    42   5632.0  1388.978183  1314.909129
-    43   5760.0  1392.182613  1322.860418
-    44   5888.0  1390.829754  1344.485828
-    45   6016.0  1400.598223  1357.206329
-    46   6144.0  1409.593231  1375.963080
-    47   6272.0  1417.400971  1375.945343
-    48   6400.0  1417.563908  1390.006612
-    49   6528.0  1413.700083  1391.959073
-    50   6656.0  1420.126941  1400.721054
-    51   6784.0  1410.125959  1414.339304
-    52   6912.0  1422.861146  1425.171849
-    53   7040.0  1423.867541  1430.334879
-    54   7168.0  1427.592784  1432.060799
-    55   7296.0  1432.745667  1444.003034
-    56   7424.0  1425.846728  1444.623121
-    57   7552.0  1426.069935  1454.976665
-    58   7680.0  1433.180614  1457.358139
-    59   7808.0  1434.316521  1463.133959
-    60   7936.0  1434.416999  1466.447899
-    61   8064.0  1442.578258  1475.902317
-    62   8192.0  1438.601413  1482.332501
-    63   8320.0  1387.667444  1403.935781
-    64   8448.0  1379.756958  1405.413480
-    65   8576.0  1398.347196  1396.481701
-    66   8704.0  1388.140060  1399.305828
-    67   8832.0  1380.021556  1403.700443
-    68   8960.0  1396.742877  1412.809052
-    69   9088.0  1411.205013  1417.262586
-    70   9216.0  1404.847816  1422.861046
-    71   9344.0  1399.063202  1423.671239
-    72   9472.0  1403.386138  1432.054800
-    73   9600.0  1392.939113  1432.805267
-    74   9728.0  1400.608470  1439.468593
-    75   9856.0  1415.401127  1443.895501
-    76   9984.0  1400.604934  1450.519086
-    77  10112.0  1407.370519  1457.356588
-    78  10240.0  1421.899049  1467.874429
-    79  10368.0  1414.979262  1460.652639
-    80  10496.0  1412.905634  1466.614576
-    81  10624.0  1414.302238  1468.102409
-    82  10752.0  1406.715569  1472.598736
-    83  10880.0  1404.487093  1483.610929
-    84  11008.0  1420.505975  1476.814621
-    85  11136.0  1420.352497  1486.673357
-    86  11264.0  1428.341970  1485.286961
-    87  11392.0  1416.208044  1487.859030
-    88  11520.0  1425.733259  1492.494322
-    89  11648.0  1426.856333  1495.201893
-    90  11776.0  1432.751878  1502.286399
-    91  11904.0  1444.235182  1505.544131
-    92  12032.0  1420.752782  1506.427285
-    93  12160.0  1414.192482  1510.118754
-    94  12288.0  1434.837677  1392.817331
-    95  12416.0  1448.873765  1390.955443
-    96  12544.0  1442.313757  1395.992982
-    97  12672.0  1445.693051  1392.608451
+    0     256.0   472.248392   701.885023
+    1     384.0   614.817494   809.484396
+    2     512.0   749.718519   928.641386
+    3     640.0   784.034078   941.941785
+    4     768.0   873.485351  1015.580831
+    5     896.0   925.328916  1059.315069
+    6    1024.0   988.681863  1123.623656
+    7    1152.0  1110.861679   614.879126
+    8    1280.0  1138.762802   669.488146
+    9    1408.0  1165.902553   721.218459
+    10   1536.0  1192.501409   779.548560
+    11   1664.0  1218.737519   811.238654
+    12   1792.0  1240.802079   863.432376
+    13   1920.0  1249.786493   909.492869
+    14   2048.0  1276.310734   959.232739
+    15   2176.0  1265.457375   978.246089
+    16   2304.0  1265.541515  1007.133168
+    17   2432.0  1300.501390  1052.120148
+    18   2560.0  1297.753634  1082.321009
+    19   2688.0  1312.779873  1103.824881
+    20   2816.0  1327.978661  1126.692791
+    21   2944.0  1329.596385  1167.193171
+    22   3072.0  1346.206218  1185.827685
+    23   3200.0  1353.570718  1191.588360
+    24   3328.0  1357.615911  1227.687578
+    25   3456.0  1371.980332  1249.832871
+    26   3584.0  1379.705264  1258.646574
+    27   3712.0  1382.418886  1268.619219
+    28   3840.0  1390.688705  1300.701633
+    29   3968.0  1384.527171  1313.374549
+    30   4096.0  1395.849637  1327.319867
+    31   4224.0  1340.446202  1162.015562
+    32   4352.0  1337.784046  1175.697617
+    33   4480.0  1357.398945  1183.431233
+    34   4608.0  1362.600860  1196.670325
+    35   4736.0  1359.884590  1196.286151
+    36   4864.0  1372.809967  1223.546378
+    37   4992.0  1369.637678  1238.270336
+    38   5120.0  1379.879914  1251.992727
+    39   5248.0  1372.198573  1258.378565
+    40   5376.0  1378.474027  1285.996977
+    41   5504.0  1382.872158  1298.895650
+    42   5632.0  1386.859605  1314.592582
+    43   5760.0  1393.175791  1324.653233
+    44   5888.0  1386.276063  1340.996018
+    45   6016.0  1398.512185  1354.368086
+    46   6144.0  1409.673532  1377.859132
+    47   6272.0  1415.823594  1375.928048
+    48   6400.0  1414.224254  1387.843621
+    49   6528.0  1414.250498  1396.702706
+    50   6656.0  1418.889169  1405.266578
+    51   6784.0  1413.503890  1415.482661
+    52   6912.0  1429.825258  1421.813798
+    53   7040.0  1423.019561  1427.824577
+    54   7168.0  1425.240013  1435.964815
+    55   7296.0  1428.480686  1441.556075
+    56   7424.0  1429.922167  1444.834075
+    57   7552.0  1430.845355  1454.683789
+    58   7680.0  1438.646380  1458.203105
+    59   7808.0  1435.234431  1466.637497
+    60   7936.0  1440.966366  1466.399596
+    61   8064.0  1438.892102  1472.633345
+    62   8192.0  1440.564822  1483.176195
+    63   8320.0  1388.404367  1401.034126
+    64   8448.0  1380.932023  1402.220449
+    65   8576.0  1395.314163  1397.291445
+    66   8704.0  1391.488788  1398.187149
+    67   8832.0  1380.915247  1402.202383
+    68   8960.0  1397.044141  1411.398781
+    69   9088.0  1405.968816  1415.957982
+    70   9216.0  1398.564510  1422.908998
+    71   9344.0  1397.731969  1424.692509
+    72   9472.0  1402.548695  1435.356776
+    73   9600.0  1396.168398  1435.868546
+    74   9728.0  1401.887600  1438.345683
+    75   9856.0  1417.406069  1444.719090
+    76   9984.0  1397.929896  1451.207394
+    77  10112.0  1412.401782  1458.073005
+    78  10240.0  1415.380452  1466.725280
+    79  10368.0  1409.530247  1461.191186
+    80  10496.0  1415.231142  1465.841584
+    81  10624.0  1411.417319  1465.200247
+    82  10752.0  1403.577538  1474.710333
+    83  10880.0  1393.192674  1477.071274
+    84  11008.0  1418.647024  1479.430277
+    85  11136.0  1421.044680  1486.316754
+    86  11264.0  1429.734468  1486.172510
+    87  11392.0  1415.070802  1491.852809
+    88  11520.0  1424.279979  1493.777990
+    89  11648.0  1425.020236  1498.114879
+    90  11776.0  1429.744479  1500.415311
+    91  11904.0  1441.974837  1508.847820
+    92  12032.0  1426.245477  1509.024198
+    93  12160.0  1421.983141  1511.923434
+    94  12288.0  1437.280346  1393.701942
+    95  12416.0  1450.854757  1390.598106
+    96  12544.0  1435.618330  1392.801912
+    97  12672.0  1448.780594  1392.126876
 
 
 
@@ -415,7 +415,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 29.550 seconds)
+   **Total running time of the script:** (0 minutes 23.406 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

diff --git a/main/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt b/main/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt
@@ -574,73 +574,73 @@ but feel free to arrange this script as you wish to benchmark any other matrix s
     2    512.0   512.0   512.0   26.214401   26.214401
     3    640.0   640.0   640.0   42.666665   42.666665
     4    768.0   768.0   768.0   63.195428   63.195428
-    5    896.0   896.0   896.0   78.051553   87.808000
-    6   1024.0  1024.0  1024.0  110.376426   99.864382
+    5    896.0   896.0   896.0   78.051553   93.661869
+    6   1024.0  1024.0  1024.0  104.857603   99.864382
     7   1152.0  1152.0  1152.0  135.726544  129.825388
     8   1280.0  1280.0  1280.0  157.538463  163.840004
-    9   1408.0  1408.0  1408.0  151.438217  132.970149
-    10  1536.0  1536.0  1536.0  176.947204  157.286398
-    11  1664.0  1664.0  1664.0  179.978245  179.978245
+    9   1408.0  1408.0  1408.0  155.765024  132.970149
+    10  1536.0  1536.0  1536.0  176.947204  153.867127
+    11  1664.0  1664.0  1664.0  179.978245  176.449258
     12  1792.0  1792.0  1792.0  172.914215  204.353162
     13  1920.0  1920.0  1920.0  200.347822  166.554219
     14  2048.0  2048.0  2048.0  223.696203  190.650180
     15  2176.0  2176.0  2176.0  211.827867  209.621326
-    16  2304.0  2304.0  2304.0  227.503545  229.691080
-    17  2432.0  2432.0  2432.0  203.583068  202.118452
-    18  2560.0  2560.0  2560.0  222.911566  222.911566
-    19  2688.0  2688.0  2688.0  200.704002  198.602388
-    20  2816.0  2816.0  2816.0  212.752230  211.719459
-    21  2944.0  2944.0  2944.0  222.482283  218.579083
-    22  3072.0  3072.0  3072.0  208.173173  211.280236
-    23  3200.0  3200.0  3200.0  232.727274  220.689658
-    24  3328.0  3328.0  3328.0  207.467716  208.670419
-    25  3456.0  3456.0  3456.0  208.864166  217.308808
-    26  3584.0  3584.0  3584.0  218.772251  212.565943
-    27  3712.0  3712.0  3712.0  213.000737  213.912940
-    28  3840.0  3840.0  3840.0  210.250955  210.651436
-    29  3968.0  3968.0  3968.0  212.215536  214.077090
-    30  4096.0  4096.0  4096.0  222.214781  216.480204
+    16  2304.0  2304.0  2304.0  231.921091  229.691080
+    17  2432.0  2432.0  2432.0  205.069087  202.118452
+    18  2560.0  2560.0  2560.0  224.438347  219.919464
+    19  2688.0  2688.0  2688.0  199.647657  197.567993
+    20  2816.0  2816.0  2816.0  211.719459  212.752230
+    21  2944.0  2944.0  2944.0  221.493479  221.493479
+    22  3072.0  3072.0  3072.0  208.941345  211.280236
+    23  3200.0  3200.0  3200.0  214.046818  219.931269
+    24  3328.0  3328.0  3328.0  205.103410  208.067338
+    25  3456.0  3456.0  3456.0  217.308808  217.308808
+    26  3584.0  3584.0  3584.0  221.466479  212.565943
+    27  3712.0  3712.0  3712.0  208.990259  216.228019
+    28  3840.0  3840.0  3840.0  209.851994  210.651436
+    29  3968.0  3968.0  3968.0  210.749463  218.289686
+    30  4096.0  4096.0  4096.0  217.180793  219.310012
     matmul-performance-fp8:
              M       N       K      Triton
-    0    256.0   256.0   256.0    2.978909
+    0    256.0   256.0   256.0    3.276800
     1    384.0   384.0   384.0    9.216000
-    2    512.0   512.0   512.0   18.724571
+    2    512.0   512.0   512.0   20.164923
     3    640.0   640.0   640.0   34.133334
-    4    768.0   768.0   768.0   42.130286
+    4    768.0   768.0   768.0   40.215272
     5    896.0   896.0   896.0   58.538665
     6   1024.0  1024.0  1024.0   63.550060
     7   1152.0  1152.0  1152.0   80.702267
     8   1280.0  1280.0  1280.0  102.400003
     9   1408.0  1408.0  1408.0   82.602666
-    10  1536.0  1536.0  1536.0   98.303997
+    10  1536.0  1536.0  1536.0   99.688560
     11  1664.0  1664.0  1664.0  116.868992
     12  1792.0  1792.0  1792.0  133.802668
     13  1920.0  1920.0  1920.0   99.453240
-    14  2048.0  2048.0  2048.0  113.359563
+    14  2048.0  2048.0  2048.0  114.130722
     15  2176.0  2176.0  2176.0  121.226797
-    16  2304.0  2304.0  2304.0  134.959733
+    16  2304.0  2304.0  2304.0  135.726544
     17  2432.0  2432.0  2432.0  131.898888
-    18  2560.0  2560.0  2560.0  146.941707
-    19  2688.0  2688.0  2688.0  117.439807
-    20  2816.0  2816.0  2816.0  129.036114
-    21  2944.0  2944.0  2944.0  140.383190
-    22  3072.0  3072.0  3072.0  144.079147
-    23  3200.0  3200.0  3200.0  139.130432
-    24  3328.0  3328.0  3328.0  131.370982
-    25  3456.0  3456.0  3456.0  139.242781
-    26  3584.0  3584.0  3584.0  148.620481
+    18  2560.0  2560.0  2560.0  146.285712
+    19  2688.0  2688.0  2688.0  118.171514
+    20  2816.0  2816.0  2816.0  129.419013
+    21  2944.0  2944.0  2944.0  139.596724
+    22  3072.0  3072.0  3072.0  144.446699
+    23  3200.0  3200.0  3200.0  140.350874
+    24  3328.0  3328.0  3328.0  131.131689
+    25  3456.0  3456.0  3456.0  139.725414
+    26  3584.0  3584.0  3584.0  148.866543
     27  3712.0  3712.0  3712.0  141.297511
     28  3840.0  3840.0  3840.0  138.240003
-    29  3968.0  3968.0  3968.0  145.787254
-    30  4096.0  4096.0  4096.0  156.430916
+    29  3968.0  3968.0  3968.0  145.613293
+    30  4096.0  4096.0  4096.0  155.344592
 
 
 
 
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (2 minutes 17.540 seconds)
+   **Total running time of the script:** (2 minutes 17.183 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

diff --git a/main/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt b/main/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt
@@ -242,7 +242,7 @@ References
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 0.702 seconds)
+   **Total running time of the script:** (0 minutes 0.692 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py: