diff --git a/master/.buildinfo b/master/.buildinfo index ab3a184d6..a0fa2e401 100644 --- a/master/.buildinfo +++ b/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: 0fcd5abde7bfabe2e08b7074ee29547d +config: 4c0877428b2c1069ae413f72ef998a08 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index 893ec33bd..8b7b60e43 100644 Binary files a/master/.doctrees/environment.pickle and b/master/.doctrees/environment.pickle differ diff --git a/master/.doctrees/getting-started/installation.doctree b/master/.doctrees/getting-started/installation.doctree index f941bda7c..a22702358 100644 Binary files a/master/.doctrees/getting-started/installation.doctree and b/master/.doctrees/getting-started/installation.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/01-vector-add.doctree b/master/.doctrees/getting-started/tutorials/01-vector-add.doctree index b7285e970..45e6d0a66 100644 Binary files a/master/.doctrees/getting-started/tutorials/01-vector-add.doctree and b/master/.doctrees/getting-started/tutorials/01-vector-add.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/02-fused-softmax.doctree b/master/.doctrees/getting-started/tutorials/02-fused-softmax.doctree index 99c067544..bd449a7e9 100644 Binary files a/master/.doctrees/getting-started/tutorials/02-fused-softmax.doctree and b/master/.doctrees/getting-started/tutorials/02-fused-softmax.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree b/master/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree index 4a009a603..d7843ff9f 100644 Binary files a/master/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree and b/master/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree b/master/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree index b2ce44540..7f229496c 100644 Binary files a/master/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree and b/master/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/05-layer-norm.doctree b/master/.doctrees/getting-started/tutorials/05-layer-norm.doctree index a41766cba..71a4b813c 100644 Binary files a/master/.doctrees/getting-started/tutorials/05-layer-norm.doctree and b/master/.doctrees/getting-started/tutorials/05-layer-norm.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/06-fused-attention.doctree b/master/.doctrees/getting-started/tutorials/06-fused-attention.doctree index 32af30ea5..c22cb3937 100644 Binary files a/master/.doctrees/getting-started/tutorials/06-fused-attention.doctree and b/master/.doctrees/getting-started/tutorials/06-fused-attention.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/07-libdevice-function.doctree b/master/.doctrees/getting-started/tutorials/07-libdevice-function.doctree index c53b982b9..04a7e9976 100644 Binary files a/master/.doctrees/getting-started/tutorials/07-libdevice-function.doctree and b/master/.doctrees/getting-started/tutorials/07-libdevice-function.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/index.doctree b/master/.doctrees/getting-started/tutorials/index.doctree index a42d0c19d..cc9e5088b 100644 Binary files a/master/.doctrees/getting-started/tutorials/index.doctree and b/master/.doctrees/getting-started/tutorials/index.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/sg_execution_times.doctree b/master/.doctrees/getting-started/tutorials/sg_execution_times.doctree index ed5505003..cd4de0317 100644 Binary files a/master/.doctrees/getting-started/tutorials/sg_execution_times.doctree and b/master/.doctrees/getting-started/tutorials/sg_execution_times.doctree differ diff --git a/master/.doctrees/index.doctree b/master/.doctrees/index.doctree index d0bac6f8a..90f8b4572 100644 Binary files a/master/.doctrees/index.doctree and b/master/.doctrees/index.doctree differ diff --git a/master/.doctrees/programming-guide/chapter-1/introduction.doctree b/master/.doctrees/programming-guide/chapter-1/introduction.doctree index 5344b5190..723de5df5 100644 Binary files a/master/.doctrees/programming-guide/chapter-1/introduction.doctree and b/master/.doctrees/programming-guide/chapter-1/introduction.doctree differ diff --git a/master/.doctrees/programming-guide/chapter-2/related-work.doctree b/master/.doctrees/programming-guide/chapter-2/related-work.doctree index 9710911cc..5f8df809f 100644 Binary files a/master/.doctrees/programming-guide/chapter-2/related-work.doctree and b/master/.doctrees/programming-guide/chapter-2/related-work.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.Config.doctree b/master/.doctrees/python-api/generated/triton.Config.doctree index 6d94d59f3..871f6f013 100644 Binary files a/master/.doctrees/python-api/generated/triton.Config.doctree and b/master/.doctrees/python-api/generated/triton.Config.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.autotune.doctree b/master/.doctrees/python-api/generated/triton.autotune.doctree index 013d6dad4..db37b704c 100644 Binary files a/master/.doctrees/python-api/generated/triton.autotune.doctree and b/master/.doctrees/python-api/generated/triton.autotune.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.heuristics.doctree b/master/.doctrees/python-api/generated/triton.heuristics.doctree index ae713bc84..437b601c7 100644 Binary files a/master/.doctrees/python-api/generated/triton.heuristics.doctree and b/master/.doctrees/python-api/generated/triton.heuristics.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.jit.doctree b/master/.doctrees/python-api/generated/triton.jit.doctree index 72cda64f9..473d50a68 100644 Binary files a/master/.doctrees/python-api/generated/triton.jit.doctree and b/master/.doctrees/python-api/generated/triton.jit.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.arange.doctree b/master/.doctrees/python-api/generated/triton.language.arange.doctree index f5ea3c941..75bee61ef 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.arange.doctree and b/master/.doctrees/python-api/generated/triton.language.arange.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_add.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_add.doctree index ad9e5aefc..7c016b5e2 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_add.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_add.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_and.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_and.doctree index c2585df2a..509fded58 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_and.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_and.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_cas.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_cas.doctree index 8d0a0f379..e54f3969d 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_cas.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_cas.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_max.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_max.doctree index e1ca0db08..187aebaf0 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_max.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_max.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_min.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_min.doctree index b52ab6afe..fe2a1cb60 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_min.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_min.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_or.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_or.doctree index bdb71e429..c63b5a262 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_or.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_or.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_xchg.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_xchg.doctree index b69501e34..a910ae841 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_xchg.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_xchg.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_xor.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_xor.doctree index 1a1065887..62bfa910d 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_xor.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_xor.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.broadcast_to.doctree b/master/.doctrees/python-api/generated/triton.language.broadcast_to.doctree index 065a84984..57185ed8d 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.broadcast_to.doctree and b/master/.doctrees/python-api/generated/triton.language.broadcast_to.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.cos.doctree b/master/.doctrees/python-api/generated/triton.language.cos.doctree index fe4ce72b5..3a9f46201 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.cos.doctree and b/master/.doctrees/python-api/generated/triton.language.cos.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.dot.doctree b/master/.doctrees/python-api/generated/triton.language.dot.doctree index 9b9056f51..3630cbaf6 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.dot.doctree and b/master/.doctrees/python-api/generated/triton.language.dot.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.exp.doctree b/master/.doctrees/python-api/generated/triton.language.exp.doctree index 59b67e8ff..0be827383 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.exp.doctree and b/master/.doctrees/python-api/generated/triton.language.exp.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.load.doctree b/master/.doctrees/python-api/generated/triton.language.load.doctree index bb659cdb3..7c07b1dc8 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.load.doctree and b/master/.doctrees/python-api/generated/triton.language.load.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.log.doctree b/master/.doctrees/python-api/generated/triton.language.log.doctree index 5269f6560..cbba29e98 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.log.doctree and b/master/.doctrees/python-api/generated/triton.language.log.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.max.doctree b/master/.doctrees/python-api/generated/triton.language.max.doctree index 46eb7d118..f5ee1abf3 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.max.doctree and b/master/.doctrees/python-api/generated/triton.language.max.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.maximum.doctree b/master/.doctrees/python-api/generated/triton.language.maximum.doctree index a1476b85b..ac3c68f5d 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.maximum.doctree and b/master/.doctrees/python-api/generated/triton.language.maximum.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.min.doctree b/master/.doctrees/python-api/generated/triton.language.min.doctree index cf3fec00a..649939d92 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.min.doctree and b/master/.doctrees/python-api/generated/triton.language.min.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.minimum.doctree b/master/.doctrees/python-api/generated/triton.language.minimum.doctree index 4619b7e6d..647a1af64 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.minimum.doctree and b/master/.doctrees/python-api/generated/triton.language.minimum.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.multiple_of.doctree b/master/.doctrees/python-api/generated/triton.language.multiple_of.doctree index 740c73ab0..ff9867f1c 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.multiple_of.doctree and b/master/.doctrees/python-api/generated/triton.language.multiple_of.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.num_programs.doctree b/master/.doctrees/python-api/generated/triton.language.num_programs.doctree index bf57cfbb9..7a05dd5c6 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.num_programs.doctree and b/master/.doctrees/python-api/generated/triton.language.num_programs.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.program_id.doctree b/master/.doctrees/python-api/generated/triton.language.program_id.doctree index 9a98261f2..00682cb62 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.program_id.doctree and b/master/.doctrees/python-api/generated/triton.language.program_id.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.rand.doctree b/master/.doctrees/python-api/generated/triton.language.rand.doctree index 77d2bbad0..d9866c0ed 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.rand.doctree and b/master/.doctrees/python-api/generated/triton.language.rand.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.randint.doctree b/master/.doctrees/python-api/generated/triton.language.randint.doctree index 0492aa84b..1c9a39021 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.randint.doctree and b/master/.doctrees/python-api/generated/triton.language.randint.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.randint4x.doctree b/master/.doctrees/python-api/generated/triton.language.randint4x.doctree index e22113003..2c5543f5e 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.randint4x.doctree and b/master/.doctrees/python-api/generated/triton.language.randint4x.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.randn.doctree b/master/.doctrees/python-api/generated/triton.language.randn.doctree index ded5d605b..2e9b23eb4 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.randn.doctree and b/master/.doctrees/python-api/generated/triton.language.randn.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.ravel.doctree b/master/.doctrees/python-api/generated/triton.language.ravel.doctree index c5e93310e..f3e6ab264 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.ravel.doctree and b/master/.doctrees/python-api/generated/triton.language.ravel.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.reshape.doctree b/master/.doctrees/python-api/generated/triton.language.reshape.doctree index 05fc1307e..96781d1e4 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.reshape.doctree and b/master/.doctrees/python-api/generated/triton.language.reshape.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.sigmoid.doctree b/master/.doctrees/python-api/generated/triton.language.sigmoid.doctree index c33977530..dd754ac67 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.sigmoid.doctree and b/master/.doctrees/python-api/generated/triton.language.sigmoid.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.sin.doctree b/master/.doctrees/python-api/generated/triton.language.sin.doctree index 957a0fd5f..02cffe6ac 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.sin.doctree and b/master/.doctrees/python-api/generated/triton.language.sin.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.softmax.doctree b/master/.doctrees/python-api/generated/triton.language.softmax.doctree index f2f13671d..214f74441 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.softmax.doctree and b/master/.doctrees/python-api/generated/triton.language.softmax.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.sqrt.doctree b/master/.doctrees/python-api/generated/triton.language.sqrt.doctree index 7b4a6ad6a..68b122dd7 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.sqrt.doctree and b/master/.doctrees/python-api/generated/triton.language.sqrt.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.store.doctree b/master/.doctrees/python-api/generated/triton.language.store.doctree index 902e816ee..a2dfb09d0 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.store.doctree and b/master/.doctrees/python-api/generated/triton.language.store.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.sum.doctree b/master/.doctrees/python-api/generated/triton.language.sum.doctree index 950f0d593..29342f928 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.sum.doctree and b/master/.doctrees/python-api/generated/triton.language.sum.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.where.doctree b/master/.doctrees/python-api/generated/triton.language.where.doctree index 1a152f5f7..3e4d52a8c 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.where.doctree and b/master/.doctrees/python-api/generated/triton.language.where.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.zeros.doctree b/master/.doctrees/python-api/generated/triton.language.zeros.doctree index 638a06f7e..fb3027e75 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.zeros.doctree and b/master/.doctrees/python-api/generated/triton.language.zeros.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.testing.Benchmark.doctree b/master/.doctrees/python-api/generated/triton.testing.Benchmark.doctree index 4f592439e..d8b0850fc 100644 Binary files a/master/.doctrees/python-api/generated/triton.testing.Benchmark.doctree and b/master/.doctrees/python-api/generated/triton.testing.Benchmark.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.testing.do_bench.doctree b/master/.doctrees/python-api/generated/triton.testing.do_bench.doctree index d8b5bdef1..179f9549c 100644 Binary files a/master/.doctrees/python-api/generated/triton.testing.do_bench.doctree and b/master/.doctrees/python-api/generated/triton.testing.do_bench.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.testing.perf_report.doctree b/master/.doctrees/python-api/generated/triton.testing.perf_report.doctree index f39bdd078..50861f18e 100644 Binary files a/master/.doctrees/python-api/generated/triton.testing.perf_report.doctree and b/master/.doctrees/python-api/generated/triton.testing.perf_report.doctree differ diff --git a/master/.doctrees/python-api/triton.doctree b/master/.doctrees/python-api/triton.doctree index 95a667788..32311629b 100644 Binary files a/master/.doctrees/python-api/triton.doctree and b/master/.doctrees/python-api/triton.doctree differ diff --git a/master/.doctrees/python-api/triton.language.doctree b/master/.doctrees/python-api/triton.language.doctree index 7caa84f24..f556b476b 100644 Binary files a/master/.doctrees/python-api/triton.language.doctree and b/master/.doctrees/python-api/triton.language.doctree differ diff --git a/master/.doctrees/python-api/triton.testing.doctree b/master/.doctrees/python-api/triton.testing.doctree index d01d541f1..c6ed684e2 100644 Binary files a/master/.doctrees/python-api/triton.testing.doctree and b/master/.doctrees/python-api/triton.testing.doctree differ diff --git a/master/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip b/master/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip index 240630e82..0f596a058 100644 Binary files a/master/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip and b/master/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip differ diff --git a/master/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip b/master/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip index 2045df6ce..3618cb80b 100644 Binary files a/master/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip and b/master/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip differ diff --git a/master/_images/sphx_glr_01-vector-add_001.png b/master/_images/sphx_glr_01-vector-add_001.png index 80b2a3c13..1c62c1122 100644 Binary files a/master/_images/sphx_glr_01-vector-add_001.png and b/master/_images/sphx_glr_01-vector-add_001.png differ diff --git a/master/_images/sphx_glr_01-vector-add_thumb.png b/master/_images/sphx_glr_01-vector-add_thumb.png index 061a977c2..6ba60d634 100644 Binary files a/master/_images/sphx_glr_01-vector-add_thumb.png and b/master/_images/sphx_glr_01-vector-add_thumb.png differ diff --git a/master/_images/sphx_glr_02-fused-softmax_001.png b/master/_images/sphx_glr_02-fused-softmax_001.png index 714c2e81c..fe88bc9ae 100644 Binary files a/master/_images/sphx_glr_02-fused-softmax_001.png and b/master/_images/sphx_glr_02-fused-softmax_001.png differ diff --git a/master/_images/sphx_glr_02-fused-softmax_thumb.png b/master/_images/sphx_glr_02-fused-softmax_thumb.png index 86479edd2..f52cf4a16 100644 Binary files a/master/_images/sphx_glr_02-fused-softmax_thumb.png and b/master/_images/sphx_glr_02-fused-softmax_thumb.png differ diff --git a/master/_images/sphx_glr_03-matrix-multiplication_001.png b/master/_images/sphx_glr_03-matrix-multiplication_001.png index 62f3a4397..76042963c 100644 Binary files a/master/_images/sphx_glr_03-matrix-multiplication_001.png and b/master/_images/sphx_glr_03-matrix-multiplication_001.png differ diff --git a/master/_images/sphx_glr_03-matrix-multiplication_thumb.png b/master/_images/sphx_glr_03-matrix-multiplication_thumb.png index 1fe23fc8e..1424f8acc 100644 Binary files a/master/_images/sphx_glr_03-matrix-multiplication_thumb.png and b/master/_images/sphx_glr_03-matrix-multiplication_thumb.png differ diff --git a/master/_images/sphx_glr_05-layer-norm_001.png b/master/_images/sphx_glr_05-layer-norm_001.png index 0b7b0f9f6..200ab82b1 100644 Binary files a/master/_images/sphx_glr_05-layer-norm_001.png and b/master/_images/sphx_glr_05-layer-norm_001.png differ diff --git a/master/_images/sphx_glr_05-layer-norm_thumb.png b/master/_images/sphx_glr_05-layer-norm_thumb.png index 0368880fc..decd0114b 100644 Binary files a/master/_images/sphx_glr_05-layer-norm_thumb.png and b/master/_images/sphx_glr_05-layer-norm_thumb.png differ diff --git a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt index da2df817c..0ca329f77 100644 --- a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -232,13 +232,13 @@ 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 9.600000 9.600000 + 0 4096.0 8.000000 9.600000 1 8192.0 19.200000 19.200000 - 2 16384.0 31.999999 31.999999 + 2 16384.0 38.400001 38.400001 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 341.333321 + 6 262144.0 384.000001 384.000001 7 524288.0 472.615390 472.615390 8 1048576.0 614.400016 614.400016 9 2097152.0 722.823517 722.823517 @@ -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 46.509 seconds) + **Total running time of the script:** ( 1 minutes 45.741 seconds) .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py: diff --git a/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt b/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt index ef76c1910..4c98bcb9b 100644 --- a/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt +++ b/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt @@ -285,10 +285,10 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t 4 768.0 722.823517 664.216187 162.754967 .. ... ... ... ... 93 12160.0 812.359066 406.179533 198.631953 - 94 12288.0 812.429770 415.661740 198.895304 + 94 12288.0 812.429770 415.661740 198.995960 95 12416.0 812.498981 412.149375 198.556711 - 96 12544.0 812.566838 412.971190 198.864492 - 97 12672.0 811.007961 412.097543 198.873965 + 96 12544.0 810.925276 412.546756 198.815254 + 97 12672.0 811.007961 411.888249 198.873965 [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 30.010 seconds) + **Total running time of the script:** ( 3 minutes 29.799 seconds) .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py: diff --git a/master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt b/master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt index 718d70b0d..db97a1c0a 100644 --- a/master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt +++ b/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 2.978909 ... 3.276800 2.978909 + 0 256.0 2.730667 ... 2.978909 2.978909 1 384.0 7.372800 ... 8.507077 8.507077 2 512.0 14.563555 ... 16.384000 16.384000 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 51.150050 ... 53.773130 52.428801 - 7 1152.0 45.242181 ... 48.161033 47.396572 + 6 1024.0 51.150050 ... 53.773130 53.773130 + 7 1152.0 45.242181 ... 48.161033 48.161033 8 1280.0 51.200001 ... 57.690139 57.690139 - 9 1408.0 64.138541 ... 68.147202 67.305878 - 10 1536.0 80.430545 ... 81.355034 79.526831 + 9 1408.0 64.138541 ... 69.009825 67.305878 + 10 1536.0 80.430545 ... 81.355034 78.643199 11 1664.0 62.929456 ... 63.372618 62.492442 - 12 1792.0 72.512412 ... 73.460287 59.467852 - 13 1920.0 69.120002 ... 71.257735 71.257735 + 12 1792.0 72.983276 ... 73.460287 59.467852 + 13 1920.0 68.776119 ... 71.257735 71.257735 14 2048.0 73.908442 ... 78.398206 77.314362 - 15 2176.0 83.500614 ... 87.115360 85.632545 + 15 2176.0 83.500614 ... 87.876193 86.367588 16 2304.0 68.446623 ... 78.064941 77.307030 - 17 2432.0 71.305746 ... 86.179335 75.320281 - 18 2560.0 77.833728 ... 82.539044 81.310171 - 19 2688.0 83.737433 ... 90.316801 89.254248 - 20 2816.0 79.806423 ... 84.116121 83.873477 - 21 2944.0 81.298583 ... 83.060049 83.337844 - 22 3072.0 78.643199 ... 88.335577 86.315709 - 23 3200.0 82.368085 ... 96.676741 95.665176 - 24 3328.0 83.130825 ... 84.695641 84.397770 - 25 3456.0 82.015834 ... 91.097818 90.892410 - 26 3584.0 84.865870 ... 95.451583 90.367227 - 27 3712.0 84.658765 ... 88.955779 87.018592 - 28 3840.0 84.485870 ... 89.802683 88.473602 - 29 3968.0 92.864488 ... 87.066671 89.493168 - 30 4096.0 88.417474 ... 86.258181 89.898012 + 17 2432.0 71.305746 ... 86.179335 85.653855 + 18 2560.0 77.833728 ... 82.747477 81.108913 + 19 2688.0 83.277839 ... 91.185232 89.888756 + 20 2816.0 80.173175 ... 84.035084 83.712490 + 21 2944.0 82.102191 ... 82.921853 82.784108 + 22 3072.0 81.005868 ... 89.310890 88.335577 + 23 3200.0 84.656085 ... 96.530922 95.380032 + 24 3328.0 82.843841 ... 85.602017 84.298943 + 25 3456.0 81.189898 ... 91.928814 88.986281 + 26 3584.0 86.540320 ... 88.149642 93.273228 + 27 3712.0 85.382349 ... 81.415926 87.937800 + 28 3840.0 81.198237 ... 86.063813 90.058629 + 29 3968.0 86.911637 ... 91.609561 86.175099 + 30 4096.0 93.206754 ... 82.848854 84.573239 [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 34.417 seconds) + **Total running time of the script:** ( 7 minutes 7.789 seconds) .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py: diff --git a/master/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt b/master/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt index d1778b13a..3072fe438 100644 --- a/master/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt +++ b/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 0.012 seconds) + **Total running time of the script:** ( 0 minutes 0.284 seconds) .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py: diff --git a/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt b/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt index 5adbe3627..c06fd18f9 100644 --- a/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt +++ b/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt @@ -38,21 +38,21 @@ Layer Normalization layer-norm: N Triton Torch Apex - 0 1024.0 585.142849 277.694907 468.114273 + 0 1024.0 585.142849 277.694907 481.882344 1 1536.0 630.153868 323.368435 511.999982 - 2 2048.0 682.666643 334.367358 520.126988 - 3 2560.0 694.237267 365.714281 512.000013 + 2 2048.0 668.734716 334.367358 520.126988 + 3 2560.0 694.237267 365.714281 518.481028 4 3072.0 712.347810 378.092307 501.551037 - 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 426.173427 - 8 5120.0 688.403381 397.669909 422.268057 - 9 5632.0 704.000002 396.969169 415.262685 - 10 6144.0 697.191505 402.885254 409.600010 - 11 6656.0 705.271522 400.360920 400.360920 - 12 7168.0 690.891575 396.844306 386.154893 - 13 7680.0 678.895043 393.846167 386.415087 - 14 8192.0 636.271854 393.609605 371.308771 + 5 3584.0 725.873439 384.859062 458.751978 + 6 4096.0 728.177767 381.023256 458.293714 + 7 4608.0 670.254540 396.387087 426.173427 + 8 5120.0 688.403381 397.669909 426.666652 + 9 5632.0 698.542675 395.228063 413.357796 + 10 6144.0 697.191505 402.885254 411.313806 + 11 6656.0 700.631610 400.360920 398.861429 + 12 7168.0 690.891575 396.844306 387.459443 + 13 7680.0 678.895043 392.587863 387.634072 + 14 8192.0 639.375598 393.609605 372.363633 15 8704.0 627.315309 389.005597 380.502740 16 9216.0 606.814809 407.337026 383.999986 17 9728.0 587.350922 409.599987 383.369452 @@ -60,14 +60,14 @@ Layer Normalization 19 10752.0 547.872604 411.559798 381.445676 20 11264.0 533.207081 406.826188 373.134567 21 11776.0 520.486200 409.599991 377.587162 - 22 12288.0 513.336807 413.911572 383.251457 + 22 12288.0 514.680630 414.784810 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 13824.0 482.934503 411.888257 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 376.783377 + 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 39.380 seconds) + **Total running time of the script:** ( 5 minutes 32.611 seconds) .. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py: diff --git a/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt b/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt index 94cde5de4..d78c6a14f 100644 --- a/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt +++ b/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt @@ -390,7 +390,7 @@ This is a Triton implementation of the Flash Attention algorithm .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 0 minutes 0.072 seconds) + **Total running time of the script:** ( 0 minutes 0.073 seconds) .. _sphx_glr_download_getting-started_tutorials_06-fused-attention.py: diff --git a/master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt b/master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt index 9512c1fc6..7db38fb6e 100644 --- a/master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt +++ b/master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt @@ -152,7 +152,7 @@ We can also customize the libdevice library path by passing the path to the `lib .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 0 minutes 0.009 seconds) + **Total running time of the script:** ( 0 minutes 0.254 seconds) .. _sphx_glr_download_getting-started_tutorials_07-libdevice-function.py: diff --git a/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt b/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt index 1f0052a1a..ced7f84e3 100644 --- a/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt +++ b/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt @@ -5,20 +5,20 @@ Computation times ================= -**17:30.409** total execution time for **getting-started_tutorials** files: +**17:56.551** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:34.417 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 07:07.789 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:39.380 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:32.611 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:30.010 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:29.799 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:46.509 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:45.741 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.072 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.284 | 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 | +| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.254 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.009 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.073 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/master/getting-started/tutorials/01-vector-add.html b/master/getting-started/tutorials/01-vector-add.html index 8a3f945a7..d5d92a15f 100644 --- a/master/getting-started/tutorials/01-vector-add.html +++ b/master/getting-started/tutorials/01-vector-add.html @@ -324,13 +324,13 @@ for different problem sizes.

Out:

vector-add-performance:
            size      Triton       Torch
-0        4096.0    9.600000    9.600000
+0        4096.0    8.000000    9.600000
 1        8192.0   19.200000   19.200000
-2       16384.0   31.999999   31.999999
+2       16384.0   38.400001   38.400001
 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  341.333321
+6      262144.0  384.000001  384.000001
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
 9     2097152.0  722.823517  722.823517
@@ -342,7 +342,7 @@ for different problem sizes.

 15  134217728.0  849.737435  850.656574
-

Total running time of the script: ( 1 minutes 46.509 seconds)

+

Total running time of the script: ( 1 minutes 45.741 seconds)