[GH-PAGES] Updated website

triton-lang · Jul 15, 2024 · 790f710 · 790f710
1 parent 72ead00
commit 790f710
Show file tree

Hide file tree

Showing 52 changed files with 427 additions and 427 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
@@ -230,30 +230,30 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
 
     vector-add-performance:
                size       Triton        Torch
-    0        4096.0     8.000000     9.600000
-    1        8192.0    15.999999    15.999999
-    2       16384.0    31.999999    31.999999
+    0        4096.0     8.000000     8.000000
+    1        8192.0    15.999999    19.200000
+    2       16384.0    38.400001    31.999999
     3       32768.0    63.999998    63.999998
     4       65536.0   127.999995   127.999995
     5      131072.0   219.428568   219.428568
     6      262144.0   384.000001   384.000001
     7      524288.0   614.400016   614.400016
     8     1048576.0   819.200021   819.200021
-    9     2097152.0  1023.999964  1023.999964
-    10    4194304.0  1260.307736  1228.800031
-    11    8388608.0  1424.695621  1424.695621
+    9     2097152.0  1068.521715  1023.999964
+    10    4194304.0  1260.307736  1260.307736
+    11    8388608.0  1424.695621  1404.342820
     12   16777216.0  1560.380965  1560.380965
-    13   33554432.0  1624.859540  1624.859540
+    13   33554432.0  1631.601649  1624.859540
     14   67108864.0  1669.706983  1662.646960
-    15  134217728.0  1684.008546  1678.616907
+    15  134217728.0  1684.910539  1678.616907
 
 
 
 
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 23.221 seconds)
+   **Total running time of the script:** (0 minutes 12.374 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
@@ -330,104 +330,104 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
 
     softmax-performance:
               N       Triton        Torch
-    0     256.0   472.232497   702.171465
-    1     384.0   608.221776   821.075194
-    2     512.0   748.347288   917.798130
-    3     640.0   794.010840   961.296198
-    4     768.0   880.503564  1028.055105
-    5     896.0   929.376260  1059.310371
-    6    1024.0   995.247872  1117.931778
-    7    1152.0  1098.189653   614.815704
-    8    1280.0  1142.427404   666.994096
-    9    1408.0  1157.829909   725.262518
-    10   1536.0  1186.921937   783.858897
-    11   1664.0  1212.822122   814.758900
-    12   1792.0  1234.368447   860.820173
-    13   1920.0  1252.864809   909.693041
-    14   2048.0  1280.576956   959.471738
-    15   2176.0  1259.940119   977.030864
-    16   2304.0  1270.054238  1007.618384
-    17   2432.0  1292.040622  1056.775968
-    18   2560.0  1300.951370  1081.492110
-    19   2688.0  1308.668847  1101.436478
-    20   2816.0  1322.766810  1126.968786
-    21   2944.0  1320.481193  1168.516728
-    22   3072.0  1347.621353  1186.897330
-    23   3200.0  1354.735680  1192.544341
-    24   3328.0  1358.158737  1222.205365
-    25   3456.0  1378.592802  1246.310487
-    26   3584.0  1373.627672  1262.170304
-    27   3712.0  1382.895722  1268.766714
-    28   3840.0  1392.246386  1299.335265
-    29   3968.0  1393.934656  1314.218122
-    30   4096.0  1395.595620  1327.806103
-    31   4224.0  1333.054758  1160.526936
-    32   4352.0  1333.953309  1177.872419
-    33   4480.0  1354.331708  1181.312509
-    34   4608.0  1364.438193  1192.955259
-    35   4736.0  1355.840045  1200.567689
-    36   4864.0  1375.652960  1221.137026
-    37   4992.0  1372.099181  1233.362878
-    38   5120.0  1370.727374  1251.377256
-    39   5248.0  1372.353591  1257.728505
-    40   5376.0  1381.249374  1288.770557
-    41   5504.0  1382.386006  1297.443826
-    42   5632.0  1383.427440  1317.306590
-    43   5760.0  1393.321686  1325.900646
-    44   5888.0  1389.991230  1345.828396
-    45   6016.0  1400.011271  1357.007946
-    46   6144.0  1411.739659  1372.799080
-    47   6272.0  1411.209919  1373.420837
-    48   6400.0  1412.917193  1388.638950
-    49   6528.0  1411.518521  1391.992007
-    50   6656.0  1422.172451  1404.314289
-    51   6784.0  1410.479535  1412.758827
-    52   6912.0  1426.440047  1424.460229
-    53   7040.0  1420.519206  1429.493699
-    54   7168.0  1425.657412  1435.085487
-    55   7296.0  1431.944284  1441.996978
-    56   7424.0  1434.012028  1445.675693
-    57   7552.0  1428.489410  1454.997316
-    58   7680.0  1433.415382  1459.483302
-    59   7808.0  1434.561709  1465.093566
-    60   7936.0  1436.724027  1467.875133
-    61   8064.0  1437.053110  1473.827668
-    62   8192.0  1441.930754  1484.777127
-    63   8320.0  1388.400047  1402.328873
-    64   8448.0  1386.587935  1402.189015
-    65   8576.0  1393.729646  1393.231916
-    66   8704.0  1388.585786  1397.992912
-    67   8832.0  1383.355423  1406.190219
-    68   8960.0  1398.139870  1410.866476
-    69   9088.0  1410.738999  1415.124985
-    70   9216.0  1402.342034  1420.965033
-    71   9344.0  1400.144194  1424.576350
-    72   9472.0  1398.974232  1432.841807
-    73   9600.0  1396.780397  1433.645968
-    74   9728.0  1400.012659  1441.867873
-    75   9856.0  1412.331709  1444.635793
-    76   9984.0  1404.985148  1453.193901
-    77  10112.0  1415.375788  1456.458837
-    78  10240.0  1418.165706  1464.485326
-    79  10368.0  1414.320507  1461.493163
-    80  10496.0  1411.227017  1467.779281
-    81  10624.0  1414.143348  1466.978853
-    82  10752.0  1404.296131  1470.898983
-    83  10880.0  1397.175013  1483.186017
-    84  11008.0  1418.337810  1477.105784
-    85  11136.0  1422.719982  1486.373319
-    86  11264.0  1429.399658  1485.428051
-    87  11392.0  1415.269703  1492.044734
-    88  11520.0  1422.424291  1493.268870
-    89  11648.0  1427.299673  1499.069506
-    90  11776.0  1425.655663  1502.633693
-    91  11904.0  1440.355303  1509.704958
-    92  12032.0  1419.114889  1507.287521
-    93  12160.0  1420.215425  1510.951739
-    94  12288.0  1435.442723  1392.024048
-    95  12416.0  1448.710477  1389.159282
-    96  12544.0  1442.285100  1393.181492
-    97  12672.0  1448.892684  1390.248982
+    0     256.0   476.139488   696.788258
+    1     384.0   618.827725   827.479292
+    2     512.0   760.221748   933.050692
+    3     640.0   797.744455   964.590312
+    4     768.0   881.327202  1018.776646
+    5     896.0   931.629145  1073.534358
+    6    1024.0   989.121470  1115.624655
+    7    1152.0  1111.718456   610.957464
+    8    1280.0  1147.279460   665.683488
+    9    1408.0  1164.170094   724.584712
+    10   1536.0  1184.197350   780.834636
+    11   1664.0  1209.547564   813.845228
+    12   1792.0  1237.864193   858.475756
+    13   1920.0  1254.234428   908.944638
+    14   2048.0  1272.763984   959.063498
+    15   2176.0  1264.692131   977.239079
+    16   2304.0  1275.217537  1009.596217
+    17   2432.0  1294.768054  1056.159369
+    18   2560.0  1300.226170  1083.970309
+    19   2688.0  1312.048325  1104.527304
+    20   2816.0  1328.970602  1134.579440
+    21   2944.0  1324.895257  1169.377885
+    22   3072.0  1346.332719  1184.220808
+    23   3200.0  1350.957286  1191.658986
+    24   3328.0  1353.230317  1221.801758
+    25   3456.0  1370.634023  1249.755593
+    26   3584.0  1374.222742  1256.588724
+    27   3712.0  1378.666064  1265.859437
+    28   3840.0  1389.815263  1301.320415
+    29   3968.0  1391.592430  1313.186082
+    30   4096.0  1392.912426  1324.932316
+    31   4224.0  1331.948936  1162.355169
+    32   4352.0  1332.251661  1174.758168
+    33   4480.0  1354.332825  1183.392495
+    34   4608.0  1362.559726  1193.508869
+    35   4736.0  1361.412494  1199.610872
+    36   4864.0  1374.494003  1225.630352
+    37   4992.0  1375.903904  1233.775130
+    38   5120.0  1374.668680  1250.263491
+    39   5248.0  1372.858541  1257.322491
+    40   5376.0  1375.811956  1288.827038
+    41   5504.0  1381.364907  1298.268824
+    42   5632.0  1386.009236  1312.864735
+    43   5760.0  1391.944559  1327.558803
+    44   5888.0  1392.849132  1345.422003
+    45   6016.0  1396.644789  1351.073081
+    46   6144.0  1407.104309  1375.616484
+    47   6272.0  1418.086793  1375.157333
+    48   6400.0  1417.980384  1387.342354
+    49   6528.0  1415.249498  1391.602704
+    50   6656.0  1420.331310  1405.582361
+    51   6784.0  1417.202111  1412.663309
+    52   6912.0  1432.381749  1423.158102
+    53   7040.0  1419.793560  1431.854784
+    54   7168.0  1430.581340  1436.330930
+    55   7296.0  1429.945826  1443.592076
+    56   7424.0  1428.330462  1447.402937
+    57   7552.0  1424.607809  1455.469007
+    58   7680.0  1435.101889  1458.109689
+    59   7808.0  1431.190718  1463.371140
+    60   7936.0  1437.080733  1469.151768
+    61   8064.0  1440.554513  1475.989169
+    62   8192.0  1438.506525  1483.113065
+    63   8320.0  1388.839432  1404.856624
+    64   8448.0  1380.906669  1404.087829
+    65   8576.0  1397.216183  1394.726484
+    66   8704.0  1391.153016  1400.492698
+    67   8832.0  1385.181960  1403.439253
+    68   8960.0  1396.270444  1409.371359
+    69   9088.0  1409.370731  1415.615460
+    70   9216.0  1403.434935  1422.651793
+    71   9344.0  1402.856149  1424.026237
+    72   9472.0  1396.917353  1432.801002
+    73   9600.0  1396.123339  1432.422704
+    74   9728.0  1399.535917  1439.689956
+    75   9856.0  1414.048642  1442.948339
+    76   9984.0  1401.676171  1451.736028
+    77  10112.0  1414.126083  1457.734155
+    78  10240.0  1420.305433  1466.943900
+    79  10368.0  1411.127263  1463.104160
+    80  10496.0  1416.005610  1466.565466
+    81  10624.0  1409.151943  1470.820498
+    82  10752.0  1406.087477  1473.168060
+    83  10880.0  1401.270291  1482.425922
+    84  11008.0  1424.021362  1478.111364
+    85  11136.0  1422.071915  1484.134850
+    86  11264.0  1433.532950  1490.315245
+    87  11392.0  1420.309112  1489.868394
+    88  11520.0  1422.613285  1495.584278
+    89  11648.0  1429.311198  1497.151665
+    90  11776.0  1430.830235  1501.968013
+    91  11904.0  1440.067196  1507.183144
+    92  12032.0  1420.403459  1506.206378
+    93  12160.0  1419.023122  1511.268039
+    94  12288.0  1433.554729  1393.015506
+    95  12416.0  1449.698764  1392.734374
+    96  12544.0  1441.583664  1393.369388
+    97  12672.0  1445.716152  1392.544565
 
 
 
@@ -442,7 +442,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 23.538 seconds)
+   **Total running time of the script:** (0 minutes 23.352 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
@@ -570,77 +570,77 @@ but feel free to arrange this script as you wish to benchmark any other matrix s
     matmul-performance-fp16:
              M       N       K      cuBLAS      Triton
     0    256.0   256.0   256.0    4.096000    4.096000
-    1    384.0   384.0   384.0   11.059200   12.288000
+    1    384.0   384.0   384.0   12.288000   12.288000
     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
+    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  155.765024  132.970149
-    10  1536.0  1536.0  1536.0  176.947204  153.867127
+    10  1536.0  1536.0  1536.0  176.947204  157.286398
     11  1664.0  1664.0  1664.0  179.978245  179.978245
-    12  1792.0  1792.0  1792.0  170.294302  204.353162
+    12  1792.0  1792.0  1792.0  172.914215  208.137481
     13  1920.0  1920.0  1920.0  200.347822  166.554219
-    14  2048.0  2048.0  2048.0  223.696203  188.508043
+    14  2048.0  2048.0  2048.0  226.719125  190.650180
     15  2176.0  2176.0  2176.0  211.827867  209.621326
-    16  2304.0  2304.0  2304.0  227.503545  225.357284
-    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  199.647657
+    16  2304.0  2304.0  2304.0  229.691080  227.503545
+    17  2432.0  2432.0  2432.0  203.583068  200.674737
+    18  2560.0  2560.0  2560.0  222.911566  219.919464
+    19  2688.0  2688.0  2688.0  198.602388  198.602388
     20  2816.0  2816.0  2816.0  212.752230  210.696652
-    21  2944.0  2944.0  2944.0  220.513412  223.479969
-    22  3072.0  3072.0  3072.0  208.941345  214.481453
-    23  3200.0  3200.0  3200.0  214.046818  219.178074
-    24  3328.0  3328.0  3328.0  207.467716  208.670419
-    25  3456.0  3456.0  3456.0  219.677297  214.419058
-    26  3584.0  3584.0  3584.0  216.142772  212.565943
-    27  3712.0  3712.0  3712.0  208.990259  215.761000
-    28  3840.0  3840.0  3840.0  209.851994  209.454544
-    29  3968.0  3968.0  3968.0  210.749463  213.889466
-    30  4096.0  4096.0  4096.0  221.481394  216.829933
+    21  2944.0  2944.0  2944.0  221.493479  223.479969
+    22  3072.0  3072.0  3072.0  210.494802  211.280236
+    23  3200.0  3200.0  3200.0  214.046818  215.488222
+    24  3328.0  3328.0  3328.0  207.467716  205.689424
+    25  3456.0  3456.0  3456.0  217.308808  219.677297
+    26  3584.0  3584.0  3584.0  210.082692  214.595213
+    27  3712.0  3712.0  3712.0  208.990259  218.593757
+    28  3840.0  3840.0  3840.0  207.879708  210.250955
+    29  3968.0  3968.0  3968.0  208.587935  214.077090
+    30  4096.0  4096.0  4096.0  219.668951  216.829933
     matmul-performance-fp8:
              M       N       K      Triton
-    0    256.0   256.0   256.0    2.978909
-    1    384.0   384.0   384.0   10.053818
+    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   20.164923
     3    640.0   640.0   640.0   34.133334
-    4    768.0   768.0   768.0   40.215272
+    4    768.0   768.0   768.0   42.130286
     5    896.0   896.0   896.0   58.538665
-    6   1024.0  1024.0  1024.0   61.680940
+    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  135.414749
     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  134.201527
-    17  2432.0  2432.0  2432.0  131.282542
-    18  2560.0  2560.0  2560.0  146.941707
+    17  2432.0  2432.0  2432.0  131.898888
+    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  129.036114
-    21  2944.0  2944.0  2944.0  139.206797
+    21  2944.0  2944.0  2944.0  139.596724
     22  3072.0  3072.0  3072.0  144.079147
     23  3200.0  3200.0  3200.0  138.828637
-    24  3328.0  3328.0  3328.0  131.370982
-    25  3456.0  3456.0  3456.0  138.525029
-    26  3584.0  3584.0  3584.0  149.858980
-    27  3712.0  3712.0  3712.0  141.698358
+    24  3328.0  3328.0  3328.0  131.611151
+    25  3456.0  3456.0  3456.0  138.287420
+    26  3584.0  3584.0  3584.0  148.375230
+    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  146.839878
-    30  4096.0  4096.0  4096.0  155.344592
+    29  3968.0  3968.0  3968.0  145.961642
+    30  4096.0  4096.0  4096.0  155.165002
 
 
 
 
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (2 minutes 17.064 seconds)
+   **Total running time of the script:** (2 minutes 17.000 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 0.717 seconds)
+   **Total running time of the script:** (0 minutes 0.677 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py: