Skip to content

Commit

Permalink
[GH-PAGES] Updated website
Browse files Browse the repository at this point in the history
  • Loading branch information
gh-actions-bot authored and gh-actions-bot committed Feb 18, 2025
1 parent 25eafc7 commit 4b7c6e0
Show file tree
Hide file tree
Showing 65 changed files with 429 additions and 429 deletions.
Binary file modified main/.doctrees/environment.pickle
Binary file not shown.
Binary file modified main/.doctrees/getting-started/tutorials/01-vector-add.doctree
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file modified main/.doctrees/getting-started/tutorials/05-layer-norm.doctree
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file modified main/.doctrees/getting-started/tutorials/08-grouped-gemm.doctree
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file modified main/.doctrees/sg_execution_times.doctree
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file modified main/_images/sphx_glr_01-vector-add_001.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_01-vector-add_thumb.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_02-fused-softmax_001.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_02-fused-softmax_thumb.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_03-matrix-multiplication_001.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_03-matrix-multiplication_002.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_03-matrix-multiplication_thumb.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_05-layer-norm_001.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_05-layer-norm_thumb.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_06-fused-attention_001.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_06-fused-attention_002.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_06-fused-attention_003.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_06-fused-attention_thumb.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_08-grouped-gemm_001.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified main/_images/sphx_glr_08-grouped-gemm_thumb.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
8 changes: 4 additions & 4 deletions main/_sources/getting-started/tutorials/01-vector-add.rst.txt
Original file line number Diff line number Diff line change
Expand Up @@ -232,16 +232,16 @@ 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 19.200000
0 4096.0 9.600000 8.000000
1 8192.0 15.999999 15.999999
2 16384.0 31.999999 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
9 2097152.0 1068.521715 1023.999964
10 4194304.0 1260.307736 1228.800031
11 8388608.0 1424.695621 1424.695621
12 16777216.0 1560.380965 1560.380965
Expand All @@ -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:** (0 minutes 13.070 seconds)
**Total running time of the script:** (0 minutes 7.463 seconds)


.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:
Expand Down
198 changes: 99 additions & 99 deletions main/_sources/getting-started/tutorials/02-fused-softmax.rst.txt
Original file line number Diff line number Diff line change
Expand Up @@ -321,104 +321,104 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
softmax-performance:
N Triton Torch
0 256.0 469.946288 710.308845
1 384.0 618.704045 809.746336
2 512.0 752.922502 922.805156
3 640.0 819.907826 963.302139
4 768.0 894.447136 1028.546467
5 896.0 954.649807 1063.465045
6 1024.0 1012.074935 1114.983021
7 1152.0 1101.273349 612.047585
8 1280.0 1151.075758 670.071183
9 1408.0 1169.910943 726.104761
10 1536.0 1195.890300 785.710270
11 1664.0 1211.555935 814.837377
12 1792.0 1242.741656 857.122088
13 1920.0 1249.937570 910.064099
14 2048.0 1272.047724 959.942016
15 2176.0 1246.656268 978.669237
16 2304.0 1245.498904 1013.679554
17 2432.0 1278.756538 1059.384251
18 2560.0 1292.095002 1083.922379
19 2688.0 1299.233504 1106.395640
20 2816.0 1306.581823 1134.858188
21 2944.0 1316.631079 1168.587696
22 3072.0 1334.887985 1183.186196
23 3200.0 1331.321344 1193.199071
24 3328.0 1344.742035 1223.357140
25 3456.0 1358.159046 1250.844375
26 3584.0 1356.612262 1258.225136
27 3712.0 1371.009649 1270.111437
28 3840.0 1371.026691 1302.301051
29 3968.0 1375.546013 1318.991348
30 4096.0 1379.139642 1325.363437
31 4224.0 1335.989912 1163.638550
32 4352.0 1337.175969 1174.476135
33 4480.0 1350.055821 1178.891977
34 4608.0 1365.190499 1195.634570
35 4736.0 1365.197042 1200.979387
36 4864.0 1372.251295 1220.069753
37 4992.0 1373.863844 1235.378960
38 5120.0 1373.508977 1253.588556
39 5248.0 1376.787031 1259.238777
40 5376.0 1381.831669 1285.839631
41 5504.0 1378.231091 1301.258271
42 5632.0 1383.384294 1313.999706
43 5760.0 1395.145390 1323.204534
44 5888.0 1391.486744 1340.780451
45 6016.0 1403.463443 1354.787496
46 6144.0 1412.592500 1372.859964
47 6272.0 1416.343910 1375.618625
48 6400.0 1419.268610 1390.403354
49 6528.0 1418.429610 1396.495341
50 6656.0 1420.491258 1402.071777
51 6784.0 1413.095922 1416.153509
52 6912.0 1428.636195 1424.883269
53 7040.0 1420.957508 1430.831842
54 7168.0 1426.314732 1435.528848
55 7296.0 1431.994474 1445.040929
56 7424.0 1429.175817 1447.328793
57 7552.0 1424.667269 1453.964745
58 7680.0 1434.812226 1461.651138
59 7808.0 1434.036713 1465.445063
60 7936.0 1434.757072 1469.114902
61 8064.0 1438.355135 1471.969797
62 8192.0 1436.266924 1486.568200
63 8320.0 1382.234137 1403.300604
64 8448.0 1377.273010 1405.125874
65 8576.0 1390.777590 1397.643364
66 8704.0 1387.958403 1400.658652
67 8832.0 1378.447554 1404.758350
68 8960.0 1390.880112 1413.176001
69 9088.0 1403.850958 1417.075702
70 9216.0 1394.707696 1425.860563
71 9344.0 1394.255987 1424.392213
72 9472.0 1394.414552 1436.484603
73 9600.0 1388.909473 1433.340381
74 9728.0 1393.728487 1439.451039
75 9856.0 1411.427755 1443.391620
76 9984.0 1395.337534 1449.176029
77 10112.0 1410.735999 1457.785338
78 10240.0 1414.323449 1465.422663
79 10368.0 1411.326475 1464.048878
80 10496.0 1413.592611 1463.846114
81 10624.0 1412.471989 1468.755747
82 10752.0 1399.212573 1474.500528
83 10880.0 1394.434574 1477.324217
84 11008.0 1415.217085 1479.692707
85 11136.0 1418.948518 1484.118528
86 11264.0 1425.125279 1488.043324
87 11392.0 1413.831451 1492.337949
88 11520.0 1418.260144 1496.033934
89 11648.0 1422.679999 1496.709099
90 11776.0 1420.125965 1502.713854
91 11904.0 1437.975155 1509.003819
92 12032.0 1421.591125 1507.611009
93 12160.0 1415.221175 1510.628015
94 12288.0 1428.841904 1394.316172
95 12416.0 1445.683081 1390.838175
96 12544.0 1436.072004 1390.679687
97 12672.0 1447.066932 1393.721848
0 256.0 468.788466 683.853900
1 384.0 607.838714 806.988986
2 512.0 758.840606 932.182371
3 640.0 823.143912 956.080803
4 768.0 893.529459 1023.330277
5 896.0 948.606067 1060.412716
6 1024.0 998.230457 1107.962810
7 1152.0 1103.776731 614.774875
8 1280.0 1138.242715 665.342915
9 1408.0 1165.508826 724.806027
10 1536.0 1193.801473 782.966685
11 1664.0 1210.023152 812.228640
12 1792.0 1234.656324 860.351789
13 1920.0 1255.762705 909.346111
14 2048.0 1282.311097 955.395159
15 2176.0 1235.812542 976.754764
16 2304.0 1249.431931 1006.478927
17 2432.0 1273.701243 1056.842706
18 2560.0 1286.088050 1086.055953
19 2688.0 1286.816345 1100.649322
20 2816.0 1302.423578 1132.452796
21 2944.0 1312.830828 1163.398911
22 3072.0 1331.143574 1185.217709
23 3200.0 1335.321668 1194.882215
24 3328.0 1347.553844 1226.105259
25 3456.0 1357.019364 1249.679927
26 3584.0 1349.588940 1256.363043
27 3712.0 1366.995618 1265.738743
28 3840.0 1373.451471 1299.364468
29 3968.0 1372.503695 1313.684212
30 4096.0 1378.124152 1327.859068
31 4224.0 1333.785758 1159.474743
32 4352.0 1332.027326 1172.135968
33 4480.0 1353.176112 1181.334472
34 4608.0 1366.828387 1197.381111
35 4736.0 1359.698531 1194.759714
36 4864.0 1376.782063 1222.610593
37 4992.0 1369.791743 1234.638250
38 5120.0 1377.111253 1248.372725
39 5248.0 1375.257637 1261.119132
40 5376.0 1382.036181 1287.259897
41 5504.0 1378.804520 1295.254342
42 5632.0 1388.187271 1311.202485
43 5760.0 1391.706526 1328.569019
44 5888.0 1393.864887 1343.443760
45 6016.0 1398.927630 1353.429658
46 6144.0 1408.510431 1377.510878
47 6272.0 1419.989868 1375.958474
48 6400.0 1414.184230 1391.196994
49 6528.0 1410.080859 1392.871409
50 6656.0 1421.557759 1403.407037
51 6784.0 1412.214582 1415.810744
52 6912.0 1425.787180 1424.368002
53 7040.0 1419.243591 1433.497559
54 7168.0 1429.536107 1436.298748
55 7296.0 1430.396786 1443.755975
56 7424.0 1424.718122 1443.231194
57 7552.0 1428.191581 1453.746622
58 7680.0 1435.880955 1458.840617
59 7808.0 1428.258671 1467.327792
60 7936.0 1440.026486 1469.906596
61 8064.0 1436.702429 1476.263939
62 8192.0 1437.130405 1484.226037
63 8320.0 1381.126612 1401.421766
64 8448.0 1377.816446 1400.653732
65 8576.0 1389.946171 1394.114779
66 8704.0 1384.948687 1401.467763
67 8832.0 1380.978407 1402.247509
68 8960.0 1390.479510 1411.903570
69 9088.0 1402.418922 1418.259845
70 9216.0 1399.682451 1425.525052
71 9344.0 1396.733508 1421.030202
72 9472.0 1397.098001 1436.210431
73 9600.0 1394.068470 1435.488421
74 9728.0 1395.773700 1443.221959
75 9856.0 1408.602644 1442.543686
76 9984.0 1395.386867 1450.979983
77 10112.0 1406.416581 1456.578173
78 10240.0 1413.053573 1469.313286
79 10368.0 1407.302888 1459.985490
80 10496.0 1407.177567 1465.548904
81 10624.0 1404.219485 1467.266819
82 10752.0 1403.562762 1474.148866
83 10880.0 1393.876308 1483.679013
84 11008.0 1416.355724 1476.518629
85 11136.0 1420.307517 1486.799193
86 11264.0 1426.086208 1486.535495
87 11392.0 1413.580606 1489.809625
88 11520.0 1418.975316 1493.034789
89 11648.0 1420.107245 1498.293644
90 11776.0 1425.916484 1500.826487
91 11904.0 1439.274567 1508.878942
92 12032.0 1421.952768 1508.141071
93 12160.0 1412.860754 1513.664929
94 12288.0 1426.857553 1391.418097
95 12416.0 1445.831844 1388.985988
96 12544.0 1435.622670 1392.536315
97 12672.0 1443.385321 1394.795655
Expand All @@ -433,7 +433,7 @@ In the above plot, we can see that:

.. rst-class:: sphx-glr-timing

**Total running time of the script:** (0 minutes 23.189 seconds)
**Total running time of the script:** (0 minutes 23.183 seconds)


.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -572,39 +572,39 @@ 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 12.288000 12.288000
1 384.0 384.0 384.0 11.059200 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
6 1024.0 1024.0 1024.0 104.857603 99.864382
5 896.0 896.0 896.0 78.051553 93.661869
6 1024.0 1024.0 1024.0 104.857603 95.325090
7 1152.0 1152.0 1152.0 135.726544 119.439363
8 1280.0 1280.0 1280.0 157.538463 151.703703
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 1664.0 183.651271 173.056002
12 1792.0 1792.0 1792.0 172.914215 200.703997
13 1920.0 1920.0 1920.0 200.347822 164.571430
12 1792.0 1792.0 1792.0 172.914215 197.182873
13 1920.0 1920.0 1920.0 200.347822 166.554219
14 2048.0 2048.0 2048.0 223.696203 184.365008
15 2176.0 2176.0 2176.0 209.621326 203.269178
16 2304.0 2304.0 2304.0 227.503545 221.184000
17 2432.0 2432.0 2432.0 208.107149 196.464787
18 2560.0 2560.0 2560.0 222.911566 214.169933
19 2688.0 2688.0 2688.0 199.647657 191.581096
20 2816.0 2816.0 2816.0 210.696652 201.917629
21 2944.0 2944.0 2944.0 216.678395 217.624596
22 3072.0 3072.0 3072.0 212.071554 203.680236
23 3200.0 3200.0 3200.0 216.949149 211.920530
24 3328.0 3328.0 3328.0 207.169199 203.365249
25 3456.0 3456.0 3456.0 217.308808 212.721813
26 3584.0 3584.0 3584.0 220.922331 205.286289
27 3712.0 3712.0 3712.0 209.428397 215.761000
28 3840.0 3840.0 3840.0 208.664143 206.328356
29 3968.0 3968.0 3968.0 208.587935 211.847104
30 4096.0 4096.0 4096.0 219.668951 204.600198
15 2176.0 2176.0 2176.0 211.827867 205.343354
16 2304.0 2304.0 2304.0 227.503545 219.154788
17 2432.0 2432.0 2432.0 205.069087 195.100438
18 2560.0 2560.0 2560.0 224.438347 210.051289
19 2688.0 2688.0 2688.0 198.602388 191.581096
20 2816.0 2816.0 2816.0 210.696652 205.727397
21 2944.0 2944.0 2944.0 220.513412 212.974490
22 3072.0 3072.0 3072.0 206.653671 203.680236
23 3200.0 3200.0 3200.0 211.920530 216.949149
24 3328.0 3328.0 3328.0 216.841256 206.871539
25 3456.0 3456.0 3456.0 211.605170 212.162014
26 3584.0 3584.0 3584.0 219.305830 204.353162
27 3712.0 3712.0 3712.0 210.310194 216.228019
28 3840.0 3840.0 3840.0 205.561330 206.328356
29 3968.0 3968.0 3968.0 211.847104 212.215536
30 4096.0 4096.0 4096.0 217.180793 208.736744
matmul-performance-fp8:
M N K Triton
0 256.0 256.0 256.0 4.096000
0 256.0 256.0 256.0 3.640889
1 384.0 384.0 384.0 12.288000
2 512.0 512.0 512.0 26.214401
3 640.0 640.0 640.0 46.545454
Expand All @@ -620,29 +620,29 @@ but feel free to arrange this script as you wish to benchmark any other matrix s
13 1920.0 1920.0 1920.0 160.744186
14 2048.0 2048.0 2048.0 182.361039
15 2176.0 2176.0 2176.0 173.479720
16 2304.0 2304.0 2304.0 188.093471
16 2304.0 2304.0 2304.0 191.102967
17 2432.0 2432.0 2432.0 187.296418
18 2560.0 2560.0 2560.0 188.321838
19 2688.0 2688.0 2688.0 180.633601
19 2688.0 2688.0 2688.0 179.777512
20 2816.0 2816.0 2816.0 192.983218
21 2944.0 2944.0 2944.0 193.162926
22 3072.0 3072.0 3072.0 191.942722
23 3200.0 3200.0 3200.0 190.476192
24 3328.0 3328.0 3328.0 187.966827
25 3456.0 3456.0 3456.0 190.145208
26 3584.0 3584.0 3584.0 189.096514
27 3712.0 3712.0 3712.0 188.130582
28 3840.0 3840.0 3840.0 190.675864
22 3072.0 3072.0 3072.0 190.650187
23 3200.0 3200.0 3200.0 188.790565
24 3328.0 3328.0 3328.0 187.477327
25 3456.0 3456.0 3456.0 188.809296
26 3584.0 3584.0 3584.0 190.095969
27 3712.0 3712.0 3712.0 187.776971
28 3840.0 3840.0 3840.0 187.921835
29 3968.0 3968.0 3968.0 192.466777
30 4096.0 4096.0 4096.0 195.367874
30 4096.0 4096.0 4096.0 194.800764
.. rst-class:: sphx-glr-timing

**Total running time of the script:** (2 minutes 12.994 seconds)
**Total running time of the script:** (2 minutes 13.111 seconds)


.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -246,7 +246,7 @@ References
.. rst-class:: sphx-glr-timing

**Total running time of the script:** (0 minutes 0.697 seconds)
**Total running time of the script:** (0 minutes 0.706 seconds)


.. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:
Expand Down
Loading

0 comments on commit 4b7c6e0

Please sign in to comment.