diff --git a/master/.buildinfo b/master/.buildinfo index 02e789a6b..091707d37 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: b3bec0df8b449b687a369f90243c07af +config: a4db7135b30bab5fc70265015ff5731f tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index 83fb6f1da..d5983e490 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 b568bf508..450bb17e8 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 22dab7cd7..3f8b0fca1 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 d0c8af1a3..89b0f4d39 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 c6bac0f6b..465e7b039 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 4aa33475c..8dff6b283 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 2f14efeff..cdb98d6cf 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 42a89924b..26f132685 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 7501c62d9..e280ce046 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 96a5d62f0..b26a0f352 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 c002bfc95..d549ee3e5 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 a26d54c3c..4c3b87d32 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 c2c51f0dd..d4882321c 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 a821db4c9..f36d09020 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 6ff1b9374..5e43f5a02 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 f8f8a5eac..295b8d898 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 82219450e..3c8131122 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 c7c54eabc..672461d6f 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 fc86bc3e5..6fd6df61d 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 0420bab9c..a213a9800 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 bcc70b642..3adf02e14 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 a45da5fb0..81f85e295 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 c9cd2a6aa..1c0bb9b5d 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 38da1f6c6..b053de29c 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 89831c227..fc36d46e2 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 116f934bd..ee5212ae6 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 3c918a238..eb7b8fcae 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 e24ce3f2a..c5971132c 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 f3d0a84f2..f6ba9e721 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 9d3457fd7..484c5ee5a 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 0f23447ec..99c552ccc 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 804edc898..a781be677 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 151eda432..af7c4679b 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 d6a40bf1c..f3b88be46 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 fe3994e56..f71306dcf 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 5046495e1..6363c70df 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 7d62e408d..c8af25a68 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 a3b9438da..df728c6a9 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 2891ea9e0..8c6038ff9 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 817b5538f..d9323f428 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 e0ee64069..b81a155d4 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 c793c7c80..b5b371da9 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 5a58fbd99..e467ee2ea 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 d908de86a..ea25bf98f 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 7e5e067a2..9d4991601 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 0bae4f39a..eb3637599 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 520ea4aa5..3664f26fc 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 62e183a35..b0175ab9e 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 9734df1ca..a9f5b2081 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 50f186ae4..230e32f62 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 43c42cb4f..cc5e37f5f 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 12678f2be..c51f16702 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 740951e19..1825f1dd1 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 142ca5ef4..92413f589 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 193447e75..acec60ad7 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 12e8c7ddd..7a7daab6e 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 9b358e7bc..c472afcf9 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 63829ecd2..b125f6078 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 ab3e43a45..c45d7840f 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 568a430b5..ba0bd6a28 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 18316512b..66bd13565 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 71ab5ab12..e110f8757 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 dfe63e61d..56c39e5a4 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 c5656658b..a8c86eaa7 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 c8627cab0..2af0997d9 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 97c1db3ac..8fca0fcf2 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 a2357f51c..d09694b8a 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 e4b71c822..32af098dc 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 a2d7acbea..b6cab998f 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 97e3953a0..413534deb 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 ab5f97f97..b3b976518 100644 --- a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -234,18 +234,18 @@ We can now run the decorated function above. Pass `print_data=True` to see the p size Triton Torch 0 4096.0 9.600000 9.600000 1 8192.0 19.200000 19.200000 - 2 16384.0 38.400001 38.400001 + 2 16384.0 38.400001 31.999999 3 32768.0 76.800002 76.800002 4 65536.0 127.999995 127.999995 5 131072.0 219.428568 219.428568 - 6 262144.0 384.000001 384.000001 + 6 262144.0 384.000001 341.333321 7 524288.0 472.615390 472.615390 8 1048576.0 614.400016 614.400016 9 2097152.0 722.823517 722.823517 10 4194304.0 780.190482 780.190482 11 8388608.0 812.429770 812.429770 12 16777216.0 833.084721 833.084721 - 13 33554432.0 842.004273 842.004273 + 13 33554432.0 842.004273 843.811163 14 67108864.0 847.448255 848.362445 15 134217728.0 849.737435 850.656574 @@ -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 46.910 seconds) + **Total running time of the script:** ( 1 minutes 47.482 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 9633efd11..d4d360ed5 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) - 0 256.0 546.133347 546.133347 188.321838 + 0 256.0 546.133347 546.133347 186.181817 1 384.0 614.400016 585.142862 153.600004 2 512.0 655.360017 606.814814 154.566038 - 3 640.0 706.206879 640.000002 158.759699 + 3 640.0 706.206879 640.000002 160.000000 4 768.0 722.823517 664.216187 162.754967 .. ... ... ... ... - 93 12160.0 812.359066 406.603966 198.530610 - 94 12288.0 812.429770 415.881552 198.794749 - 95 12416.0 812.498981 412.149375 198.457532 - 96 12544.0 810.925276 412.546756 198.716830 - 97 12672.0 811.007961 412.097543 198.776477 + 93 12160.0 812.359066 406.179533 198.631953 + 94 12288.0 812.429770 415.661740 198.995960 + 95 12416.0 812.498981 412.149375 198.655991 + 96 12544.0 810.925276 412.971190 198.815254 + 97 12672.0 811.007961 412.097543 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 31.136 seconds) + **Total running time of the script:** ( 3 minutes 30.502 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 8df75a390..ead180890 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 ... 3.276800 3.276800 - 1 384.0 7.372800 ... 7.899428 7.899428 - 2 512.0 14.563555 ... 15.420235 15.420235 + 0 256.0 2.978909 ... 3.276800 3.276800 + 1 384.0 7.372800 ... 7.899428 8.507077 + 2 512.0 14.563555 ... 15.420235 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 8 1280.0 51.200001 ... 57.690139 57.690139 - 9 1408.0 64.138541 ... 69.009825 67.305878 - 10 1536.0 80.430545 ... 80.430545 78.643199 + 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 72.512412 ... 73.460287 59.467852 - 13 1920.0 69.120002 ... 71.257735 71.257735 - 14 2048.0 73.908442 ... 78.033565 77.314362 - 15 2176.0 83.500614 ... 87.494120 86.367588 - 16 2304.0 68.446623 ... 77.810656 77.307030 - 17 2432.0 71.305746 ... 85.915795 85.653855 - 18 2560.0 77.833728 ... 82.331658 81.108913 - 19 2688.0 83.552988 ... 90.966561 89.888756 - 20 2816.0 80.026067 ... 84.197315 83.712490 - 21 2944.0 82.102191 ... 83.617504 82.509987 - 22 3072.0 81.825298 ... 89.451983 88.197981 - 23 3200.0 84.432717 ... 96.822991 95.808380 - 24 3328.0 83.226931 ... 85.398926 84.795401 - 25 3456.0 81.932484 ... 91.928814 88.400840 - 26 3584.0 86.540320 ... 98.375705 97.311031 - 27 3712.0 84.159518 ... 89.273764 86.118401 - 28 3840.0 84.132370 ... 93.012618 85.863352 - 29 3968.0 91.747320 ... 85.004484 87.881842 - 30 4096.0 92.820009 ... 91.804194 87.381330 + 13 1920.0 69.467336 ... 71.257735 71.257735 + 14 2048.0 73.908442 ... 78.398206 77.314362 + 15 2176.0 83.155572 ... 87.494120 85.998493 + 16 2304.0 68.251065 ... 78.064941 77.057651 + 17 2432.0 71.305746 ... 85.915795 75.320281 + 18 2560.0 78.019048 ... 82.125311 81.108913 + 19 2688.0 83.186525 ... 90.316801 89.676257 + 20 2816.0 79.879498 ... 84.360174 82.916747 + 21 2944.0 82.237674 ... 82.921853 80.510553 + 22 3072.0 82.540970 ... 89.522696 88.612060 + 23 3200.0 83.116885 ... 88.888888 96.096095 + 24 3328.0 83.275067 ... 83.808259 83.905938 + 25 3456.0 81.766291 ... 87.347312 88.400840 + 26 3584.0 87.381330 ... 99.244365 98.483450 + 27 3712.0 82.491612 ... 86.416391 87.629253 + 28 3840.0 80.197243 ... 87.114612 89.948756 + 29 3968.0 86.942599 ... 91.816356 86.296981 + 30 4096.0 93.077479 ... 85.244667 82.343743 [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:** ( 7 minutes 5.808 seconds) + **Total running time of the script:** ( 6 minutes 42.139 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 44683767b..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 0.285 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 1d66bd5bb..4ce1a0053 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 481.882344 + 0 1024.0 585.142849 277.694907 468.114273 1 1536.0 630.153868 323.368435 511.999982 - 2 2048.0 668.734716 334.367358 520.126988 + 2 2048.0 682.666643 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 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 + 4 3072.0 712.347810 378.092307 496.484863 + 5 3584.0 725.873439 384.859062 455.111115 + 6 4096.0 728.177767 381.023256 455.111095 + 7 4608.0 670.254540 394.267384 421.302872 + 8 5120.0 688.403381 397.669909 424.455959 + 9 5632.0 704.000002 395.228063 411.470331 + 10 6144.0 702.171410 402.885254 409.600010 11 6656.0 700.631610 400.360920 400.360920 - 12 7168.0 686.754468 396.844306 387.459443 - 13 7680.0 682.666656 392.587863 387.634072 - 14 8192.0 633.198054 393.609605 371.308771 + 12 7168.0 690.891575 396.844306 387.459443 + 13 7680.0 678.895043 393.846167 386.415087 + 14 8192.0 639.375598 393.609605 373.424507 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 @@ -60,12 +60,12 @@ Layer Normalization 19 10752.0 546.133312 411.559798 381.445676 20 11264.0 533.207081 406.826188 373.134567 21 11776.0 520.486200 409.599991 377.587162 - 22 12288.0 514.680630 414.784810 383.251457 + 22 12288.0 513.336807 413.911572 383.251457 23 12800.0 504.433489 410.420828 376.470582 - 24 13312.0 494.180982 405.699062 376.310952 + 24 13312.0 494.180982 405.699062 376.976995 25 13824.0 481.882350 411.888257 379.389355 - 26 14336.0 471.967074 406.695045 374.185964 - 27 14848.0 461.297068 408.192434 375.304904 + 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 @@ -393,7 +393,7 @@ Layer Normalization .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 5 minutes 31.020 seconds) + **Total running time of the script:** ( 5 minutes 40.540 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 4fef02825..63e0b2935 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 0.074 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 79c1b5c15..297ebf116 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 0.264 seconds) + **Total running time of the script:** ( 0 minutes 0.010 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 5acc91eed..2e2a8611a 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 ================= -**17:55.494** total execution time for **getting-started_tutorials** files: +**17:40.760** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 07:05.808 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:42.139 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:31.020 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:40.540 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:31.136 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:30.502 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:46.910 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:47.482 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.285 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.074 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.264 | 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_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.072 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.010 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/master/getting-started/tutorials/01-vector-add.html b/master/getting-started/tutorials/01-vector-add.html index aac55bc70..64d2c34f1 100644 --- a/master/getting-started/tutorials/01-vector-add.html +++ b/master/getting-started/tutorials/01-vector-add.html @@ -326,23 +326,23 @@ for different problem sizes.

size Triton Torch 0 4096.0 9.600000 9.600000 1 8192.0 19.200000 19.200000 -2 16384.0 38.400001 38.400001 +2 16384.0 38.400001 31.999999 3 32768.0 76.800002 76.800002 4 65536.0 127.999995 127.999995 5 131072.0 219.428568 219.428568 -6 262144.0 384.000001 384.000001 +6 262144.0 384.000001 341.333321 7 524288.0 472.615390 472.615390 8 1048576.0 614.400016 614.400016 9 2097152.0 722.823517 722.823517 10 4194304.0 780.190482 780.190482 11 8388608.0 812.429770 812.429770 12 16777216.0 833.084721 833.084721 -13 33554432.0 842.004273 842.004273 +13 33554432.0 842.004273 843.811163 14 67108864.0 847.448255 848.362445 15 134217728.0 849.737435 850.656574 -

Total running time of the script: ( 1 minutes 46.910 seconds)

+

Total running time of the script: ( 1 minutes 47.482 seconds)