diff --git a/master/.buildinfo b/master/.buildinfo index 87c31122f..176973cab 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: f96c64ba45a28721a5c3fed48369efcf +config: 0181fbac89417cfa54f7b17040b579bd tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index fb273fd77..6a38c204b 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 0118e08a5..6a862f9e0 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 db6f62691..517bc7473 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 f7c3780fe..dc5a051d2 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 bb18c3128..957983e55 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 1498b4bae..7db25df14 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 01d6ee82e..8c3c24409 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 7ac23047f..aff74bbb2 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 4faa8138f..c82a180b9 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 0aede4ea3..2c6cb4c97 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 6d5095697..3c18f3ff7 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 005bd2398..459223330 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 dc15958b0..925be5806 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 cdf7f3ba8..d49ca58aa 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 b7210e822..c583f845f 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 ec79a828a..190fb8149 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 285da5589..9fd822156 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 e9cf37922..5054a3058 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 26f685014..e299b176e 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 151b20fed..c9aba3c12 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 81ab00a2c..6098139fa 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 c43160a8e..0458cc15d 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 67725d871..3f98daae6 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 00fd1a0ef..ee4af4ab8 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 84f9e7128..cd0253651 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 d8c6b732f..4ab4ed506 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 f9810f68b..598076463 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 4fba43037..3cb5f1509 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 0779aed55..e9db39eda 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 34c3b5f28..77c676727 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 49b340860..ad89f6828 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 8f1d3cd6a..9decf75b1 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 4bbbabbb7..50b4c77f2 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 427791d1c..e2f7bdbf3 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 7d8980e0b..574975834 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 0a8d8145f..d6a58cc8d 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 5c84f68a0..c045f6154 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 dde36102f..83f910c7a 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 1f441ca16..2e0721df6 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 95daf6d72..8b1af6662 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 70d8a5016..68ac6c710 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 c23eb0605..7aaa07a87 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 c8cf3d795..2f527392b 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 15713ada2..26a274e25 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 c41668555..0ae8cc332 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 246f50142..da5a546e7 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 b59f97a1c..11fd22e49 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 adf7724d4..47b0721bc 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 f414666f0..60e50b282 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 187fbd283..9314b4b1e 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 587ed416f..c5a1e0da5 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 4935f5580..a9f8dba0b 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 3689cb660..f1625f5a5 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 ff1417e17..6701d6011 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 65a7703b1..360bc6ab4 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 6e9abedb8..ebcd1bb86 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 e9dc85ebc..16cebc6a8 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 0d633a623..111d1bdad 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 f986a3a26..e061e2c25 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 d2e6166ac..83bbbc5d7 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 7683a2980..3ec9e6071 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 c1f48545e..c1b4b5596 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 680f1f0aa..2b5b6d292 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 aebdbbc29..d5901296f 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 b72c3688c..ec6756b6a 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 d9469536c..ebeecd1d9 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 1b2f59920..7268ffe2a 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 3c5b9b7ed..c84a44faa 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 8e91539a2..1e4b7414c 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 a94b007f6..45fc7bc30 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 5fd985ea2..a1a9af19d 100644 --- a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -233,9 +233,9 @@ 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 - 1 8192.0 19.200000 19.200000 + 1 8192.0 15.999999 19.200000 2 16384.0 38.400001 38.400001 - 3 32768.0 63.999998 63.999998 + 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 @@ -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 47.206 seconds) + **Total running time of the script:** ( 1 minutes 43.980 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 60f2c6003..f9ee5bf28 100644 --- a/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt +++ b/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt @@ -278,17 +278,17 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t softmax-performance: N Triton Torch (native) Torch (jit) - 0 256.0 512.000001 512.000001 188.321838 - 1 384.0 614.400016 585.142862 153.600004 - 2 512.0 655.360017 585.142849 154.566038 - 3 640.0 706.206879 640.000002 158.759699 - 4 768.0 722.823517 664.216187 162.754967 + 0 256.0 546.133347 546.133347 188.321838 + 1 384.0 585.142862 558.545450 151.703707 + 2 512.0 655.360017 606.814814 154.566038 + 3 640.0 706.206879 640.000002 160.000000 + 4 768.0 722.823517 646.736871 163.839992 .. ... ... ... ... - 93 12160.0 812.359066 406.179533 198.733401 - 94 12288.0 812.429770 415.661740 198.995960 - 95 12416.0 810.840807 412.149375 198.655991 - 96 12544.0 810.925276 412.971190 198.913776 - 97 12672.0 811.007961 412.097543 198.971549 + 93 12160.0 812.359066 405.755985 198.936606 + 94 12288.0 812.429770 415.661740 199.197579 + 95 12416.0 812.498981 412.149375 198.904612 + 96 12544.0 810.925276 412.546756 199.012395 + 97 12672.0 811.007961 411.679167 199.167004 [98 rows x 4 columns] @@ -306,7 +306,7 @@ In the above plot, we can see that: .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 3 minutes 31.827 seconds) + **Total running time of the script:** ( 3 minutes 29.352 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 e9c2fa8da..907d41ebd 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 2.730667 ... 2.978909 2.978909 - 1 384.0 7.372800 ... 7.899428 7.899428 - 2 512.0 14.563555 ... 15.420235 15.420235 + 0 256.0 2.978909 ... 2.978909 2.978909 + 1 384.0 7.372800 ... 8.507077 8.507077 + 2 512.0 14.563555 ... 15.420235 16.384000 3 640.0 22.260869 ... 24.380953 24.380953 - 4 768.0 31.597714 ... 34.028308 34.028308 + 4 768.0 32.768000 ... 35.389441 34.028308 5 896.0 37.971025 ... 40.140799 39.025776 6 1024.0 49.932191 ... 53.773130 52.428801 - 7 1152.0 45.242181 ... 47.396572 47.396572 + 7 1152.0 45.242181 ... 48.161033 47.396572 8 1280.0 51.200001 ... 57.690139 57.690139 9 1408.0 64.138541 ... 68.147202 67.305878 - 10 1536.0 80.430545 ... 81.355034 79.526831 - 11 1664.0 62.929456 ... 63.372618 62.492442 - 12 1792.0 72.983276 ... 73.460287 59.467852 - 13 1920.0 69.467336 ... 71.257735 70.892307 - 14 2048.0 73.584279 ... 78.398206 77.314362 - 15 2176.0 83.155572 ... 87.494120 85.998493 - 16 2304.0 68.056616 ... 78.064941 77.307030 - 17 2432.0 71.125224 ... 86.179335 85.653855 - 18 2560.0 77.833728 ... 82.747477 81.512437 - 19 2688.0 83.737433 ... 90.966561 89.888756 - 20 2816.0 84.523664 ... 85.017948 84.197315 - 21 2944.0 82.034625 ... 83.899046 82.373605 - 22 3072.0 81.943708 ... 89.735509 88.890270 - 23 3200.0 84.656085 ... 96.969694 94.674553 - 24 3328.0 83.226931 ... 85.703924 84.995628 - 25 3456.0 82.519518 ... 91.928814 88.595129 - 26 3584.0 83.177979 ... 88.412386 94.947616 - 27 3712.0 85.822459 ... 84.766519 86.867254 - 28 3840.0 84.744825 ... 87.286505 86.738820 - 29 3968.0 93.219206 ... 85.992909 91.403695 - 30 4096.0 86.369197 ... 87.324485 91.804194 + 10 1536.0 80.430545 ... 80.430545 78.643199 + 11 1664.0 63.372618 ... 63.372618 62.492442 + 12 1792.0 72.983276 ... 72.983276 59.467852 + 13 1920.0 69.120002 ... 71.257735 70.892307 + 14 2048.0 73.908442 ... 78.033565 76.959706 + 15 2176.0 83.155572 ... 87.494120 86.367588 + 16 2304.0 68.446623 ... 78.064941 77.558029 + 17 2432.0 71.305746 ... 86.711310 85.134737 + 18 2560.0 77.833728 ... 82.956960 81.512437 + 19 2688.0 83.737433 ... 90.966561 89.254248 + 20 2816.0 80.173175 ... 83.392363 84.035084 + 21 2944.0 82.102191 ... 83.060049 83.337844 + 22 3072.0 80.430545 ... 89.735509 87.787755 + 23 3200.0 83.116885 ... 95.096582 96.096095 + 24 3328.0 83.419811 ... 84.447271 83.130825 + 25 3456.0 81.932484 ... 87.252780 91.407671 + 26 3584.0 87.296493 ... 99.574077 98.699661 + 27 3712.0 83.247783 ... 89.553872 81.415926 + 28 3840.0 84.679936 ... 93.405401 84.679936 + 29 3968.0 92.652949 ... 88.744681 85.361267 + 30 4096.0 91.553703 ... 85.001726 84.626564 [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 35.166 seconds) + **Total running time of the script:** ( 6 minutes 32.019 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..8c652cdd2 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 0.013 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 d67c9ffe1..fc5781c8b 100644 --- a/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt +++ b/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt @@ -39,35 +39,35 @@ Layer Normalization layer-norm: N Triton Torch Apex 0 1024.0 585.142849 277.694907 468.114273 - 1 1536.0 630.153868 323.368435 511.999982 + 1 1536.0 630.153868 327.679984 511.999982 2 2048.0 668.734716 334.367358 520.126988 - 3 2560.0 694.237267 362.477870 512.000013 - 4 3072.0 712.347810 375.206126 496.484863 - 5 3584.0 725.873439 384.859062 451.527536 - 6 4096.0 728.177767 381.023256 455.111095 - 7 4608.0 670.254540 394.267384 421.302872 + 3 2560.0 694.237267 362.477870 518.481028 + 4 3072.0 702.171410 375.206126 501.551037 + 5 3584.0 725.873439 384.859062 455.111115 + 6 4096.0 728.177767 381.023256 451.972420 + 7 4608.0 670.254540 394.267384 418.909088 8 5120.0 688.403381 397.669909 424.455959 - 9 5632.0 698.542675 395.228063 411.470331 - 10 6144.0 697.191505 402.885254 411.313806 - 11 6656.0 700.631610 398.861429 398.861429 - 12 7168.0 690.891575 396.844306 387.459443 - 13 7680.0 678.895043 392.587863 386.415087 - 14 8192.0 633.198054 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 - 18 10240.0 564.965524 408.578556 382.803739 + 9 5632.0 704.000002 395.228063 411.470331 + 10 6144.0 697.191505 402.885254 409.600010 + 11 6656.0 700.631610 398.861429 400.360920 + 12 7168.0 686.754468 394.116833 384.859062 + 13 7680.0 678.895043 393.846167 385.203746 + 14 8192.0 633.198054 388.937680 369.216905 + 15 8704.0 624.502255 390.095225 379.465939 + 16 9216.0 604.327881 407.337026 381.023249 + 17 9728.0 587.350922 408.524944 382.427505 + 18 10240.0 564.965524 409.600010 382.803739 19 10752.0 546.133312 411.559798 381.445676 - 20 11264.0 533.207081 406.826188 373.134567 + 20 11264.0 533.207081 405.909906 375.466676 21 11776.0 520.486200 409.599991 377.587162 - 22 12288.0 516.031509 413.911572 383.251457 - 23 12800.0 504.433489 410.420828 376.470582 + 22 12288.0 513.336807 413.911572 383.251457 + 23 12800.0 504.433489 409.599981 375.779805 24 13312.0 494.180982 405.699062 376.310952 - 25 13824.0 481.882350 411.122660 379.389355 - 26 14336.0 470.997935 406.695045 374.185964 - 27 14848.0 460.403127 408.192434 375.304904 - 28 15360.0 454.269882 406.214870 378.092307 - 29 15872.0 447.887117 406.974373 376.225175 + 25 13824.0 481.882350 411.888257 378.739711 + 26 14336.0 470.997935 405.257949 371.158581 + 27 14848.0 460.403127 407.492270 374.712936 + 28 15360.0 454.269882 406.887417 377.511515 + 29 15872.0 446.312810 406.974373 375.668625 @@ -393,7 +393,7 @@ Layer Normalization .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 5 minutes 41.246 seconds) + **Total running time of the script:** ( 5 minutes 37.208 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 2876c4654..622627a46 100644 --- a/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt +++ b/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt @@ -385,7 +385,7 @@ 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 297ebf116..228c0d6c8 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 0.010 seconds) + **Total running time of the script:** ( 0 minutes 0.011 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 99b934979..977a7087e 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 ================= -**17:35.538** total execution time for **getting-started_tutorials** files: +**17:22.656** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:35.166 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:32.019 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:41.246 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:37.208 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:31.827 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:29.352 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:47.206 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:43.980 | 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_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.073 | 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_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.013 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.010 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.011 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/master/getting-started/tutorials/01-vector-add.html b/master/getting-started/tutorials/01-vector-add.html index 9da2fd71a..91a52e6c6 100644 --- a/master/getting-started/tutorials/01-vector-add.html +++ b/master/getting-started/tutorials/01-vector-add.html @@ -325,9 +325,9 @@ for different problem sizes.

vector-add-performance:
            size      Triton       Torch
 0        4096.0    9.600000    9.600000
-1        8192.0   19.200000   19.200000
+1        8192.0   15.999999   19.200000
 2       16384.0   38.400001   38.400001
-3       32768.0   63.999998   63.999998
+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
@@ -342,7 +342,7 @@ for different problem sizes.

 15  134217728.0  849.737435  850.656574
-

Total running time of the script: ( 1 minutes 47.206 seconds)

+

Total running time of the script: ( 1 minutes 43.980 seconds)