diff --git a/master/.buildinfo b/master/.buildinfo index aabe6f9fb..279fa9622 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: e4b0495570fb44f14bb826391828f8cf +config: c805eb194ad6515efc001bb542757901 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index 03bec3ecb..69f576561 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 70e113857..b550d644b 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 a464456eb..485b7568d 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 d7cfa7738..8d0fd4bdc 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 b6533aec0..c69f2451b 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 86e56564b..cb1885605 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 28d895fd6..35320d916 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 bad972c94..a7ed54ece 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 ddde2ae3b..11b435f67 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 66bbe85e6..476e4d7e8 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 878d261d2..cd96abd6d 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 283540002..6a004220b 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 08791cf2b..07e65229a 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 2582138d7..af5a02573 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 e7a16d84e..80b58b910 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 2e71eec06..757fff0e9 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 a38db55e1..cd3b83101 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 e8bc257c0..96b740f74 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 f7140c1b9..4ed0fcc19 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 862cb58a6..cb0439d2b 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 e3bcb1611..7c5632fc6 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 99021751b..d27c4c9f5 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 94d360424..eca1657a0 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 9f2293e58..02f449230 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 0e948a05b..8f7875322 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 2f0c11dc4..88cc1018c 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 31917cc5c..b3c17fb55 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 e20ec842c..575b32224 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 111da5580..dc8bb2cd3 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 a7876c5a5..f83503616 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 f2a4129a7..a204ae98f 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 663428c11..ccbcd3cd8 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 71f604d81..44a476ed7 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 fc780fd38..4add36c00 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 9dcc27a71..31d98e33c 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 0eefc27a2..63dfd5f44 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 34a6d0858..c96011d78 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 eedd61482..d91ce0d11 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 1521505ba..723187f48 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 790906738..33a7a1c3a 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 d2c6a5cea..8a3a181e8 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 e53f5dbbb..c2bf200fe 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 736e95c82..66c4befa5 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 e34e9f8a5..b9622268c 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 d330ba3fb..f4f9b7e4a 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 376917921..4def2165a 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 8279f077a..bb740dbf5 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 b61f3738c..614545f7c 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 596461eaa..bff793cfe 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 0d62ef879..b9c770cd4 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 c23f43438..5a614a4ba 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 0761e4550..ea46e635a 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 08e8b72dd..59554c092 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 2271218e7..0ac3477bb 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 ba43fa230..ed51dd7c9 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 ce298530e..3c090ce2c 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 78985155a..e4fa6a110 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 6b09d3dd2..7171980bc 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 db8817646..80340285c 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 2f159a090..5f99e6235 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 0170e1307..91d15b53b 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 945ce29e9..a1f65c6d3 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 ad5ce4495..fc9af2ae3 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 3a3e369f3..b157d2077 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 67d0d8b90..a8f1746e1 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 888fca489..e8ea2beb2 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 36601a55f..e0806ba99 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 f68c6edb9..c82a1db36 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 f4bc33e38..8ac6952f4 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 1c1cbf0e7..789393c7e 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 a009d6cab..6388bb01d 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 15.999999 19.200000 + 1 8192.0 19.200000 19.200000 2 16384.0 38.400001 38.400001 - 3 32768.0 76.800002 76.800002 + 3 32768.0 63.999998 63.999998 4 65536.0 127.999995 127.999995 5 131072.0 219.428568 219.428568 6 262144.0 341.333321 384.000001 @@ -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 51.976 seconds) + **Total running time of the script:** ( 1 minutes 45.313 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 1df3527a4..74a665e0a 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 546.133347 184.089886 - 1 384.0 614.400016 585.142862 153.600004 + 0 256.0 546.133347 546.133347 188.321838 + 1 384.0 614.400016 585.142862 151.703707 2 512.0 655.360017 585.142849 154.566038 3 640.0 706.206879 640.000002 160.000000 - 4 768.0 722.823517 664.216187 162.754967 + 4 768.0 722.823517 646.736871 163.839992 .. ... ... ... ... - 93 12160.0 812.359066 405.755985 198.936606 - 94 12288.0 812.429770 415.222812 199.096718 - 95 12416.0 812.498981 412.149375 198.755369 - 96 12544.0 810.925276 412.971190 199.012395 - 97 12672.0 811.007961 412.097543 199.069228 + 93 12160.0 812.359066 405.333344 199.038365 + 94 12288.0 812.429770 415.222812 199.298541 + 95 12416.0 812.498981 411.296057 198.954424 + 96 12544.0 810.925276 412.971190 199.111113 + 97 12672.0 811.007961 412.097543 199.264875 [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 30.958 seconds) + **Total running time of the script:** ( 3 minutes 30.839 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 6b477e20f..dc116981c 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 2.978909 - 1 384.0 7.372800 ... 7.899428 7.899428 - 2 512.0 14.563555 ... 15.420235 15.420235 + 0 256.0 2.730667 ... 2.978909 2.978909 + 1 384.0 7.372800 ... 8.507077 7.899428 + 2 512.0 14.563555 ... 16.384000 16.384000 3 640.0 22.260869 ... 24.380953 24.380953 - 4 768.0 32.768000 ... 34.028308 34.028308 + 4 768.0 32.768000 ... 35.389441 34.028308 5 896.0 39.025776 ... 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 66.485074 - 10 1536.0 79.526831 ... 81.355034 79.526831 - 11 1664.0 63.372618 ... 63.372618 62.492442 - 12 1792.0 72.983276 ... 72.983276 59.154861 - 13 1920.0 68.776119 ... 71.257735 71.257735 - 14 2048.0 73.908442 ... 78.398206 77.314362 - 15 2176.0 83.500614 ... 87.494120 85.998493 - 16 2304.0 68.251065 ... 78.064941 77.307030 - 17 2432.0 71.125224 ... 86.979769 85.915795 - 18 2560.0 77.833728 ... 82.747477 81.715711 - 19 2688.0 84.295681 ... 90.966561 89.464755 - 20 2816.0 84.035084 ... 85.017948 83.233226 - 21 2944.0 82.237674 ... 83.198715 82.509987 - 22 3072.0 82.420822 ... 89.735509 87.651868 - 23 3200.0 83.333330 ... 91.168092 95.952022 - 24 3328.0 83.468170 ... 84.795401 84.895397 - 25 3456.0 81.849303 ... 90.586029 91.097818 - 26 3584.0 87.042978 ... 95.451583 97.787265 - 27 3712.0 85.785610 ... 89.194055 85.163978 - 28 3840.0 84.940091 ... 93.801526 87.148936 - 29 3968.0 92.864488 ... 87.159957 91.712842 - 30 4096.0 86.536250 ... 85.652663 90.626421 + 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 69.120002 ... 71.257735 70.892307 + 14 2048.0 73.584279 ... 78.033565 76.959706 + 15 2176.0 83.155572 ... 87.494120 85.998493 + 16 2304.0 68.446623 ... 78.064941 77.057651 + 17 2432.0 71.125224 ... 85.915795 75.320281 + 18 2560.0 77.833728 ... 82.125311 81.512437 + 19 2688.0 83.737433 ... 90.532356 89.676257 + 20 2816.0 83.074685 ... 84.687779 84.035084 + 21 2944.0 81.698415 ... 84.040530 83.060049 + 22 3072.0 81.707223 ... 90.164177 89.310890 + 23 3200.0 84.544253 ... 96.969694 95.665176 + 24 3328.0 83.905938 ... 86.320498 85.602017 + 25 3456.0 79.508447 ... 91.824110 85.585527 + 26 3584.0 85.633710 ... 92.600816 95.756542 + 27 3712.0 84.159518 ... 93.100971 87.783251 + 28 3840.0 80.901241 ... 87.980905 92.236860 + 29 3968.0 87.913500 ... 91.747320 86.114283 + 30 4096.0 93.336389 ... 86.928580 85.271746 [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 14.455 seconds) + **Total running time of the script:** ( 6 minutes 36.741 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 9eeac46b5..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 0.283 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 39bd66666..8b26041f0 100644 --- a/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt +++ b/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt @@ -40,34 +40,34 @@ Layer Normalization N Triton Torch Apex 0 1024.0 585.142849 277.694907 468.114273 1 1536.0 630.153868 323.368435 511.999982 - 2 2048.0 682.666643 337.814445 520.126988 - 3 2560.0 694.237267 362.477870 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 455.111095 - 7 4608.0 670.254540 396.387087 426.173427 - 8 5120.0 688.403381 397.669909 424.455959 - 9 5632.0 704.000002 398.725657 411.470331 - 10 6144.0 697.191505 402.885254 411.313806 - 11 6656.0 700.631610 400.360920 400.360920 - 12 7168.0 686.754468 384.859062 382.293315 - 13 7680.0 678.895043 391.337574 386.415087 - 14 8192.0 648.871301 390.095241 379.918832 - 15 8704.0 621.714277 390.095225 379.465939 + 2 2048.0 668.734716 334.367358 520.126988 + 3 2560.0 694.237267 362.477870 512.000013 + 4 3072.0 702.171410 378.092307 501.551037 + 5 3584.0 725.873439 384.859062 451.527536 + 6 4096.0 728.177767 383.251446 451.972420 + 7 4608.0 670.254540 396.387087 428.651163 + 8 5120.0 688.403381 395.748783 420.102563 + 9 5632.0 704.000002 396.969169 415.262685 + 10 6144.0 702.171410 402.885254 411.313806 + 11 6656.0 700.631610 398.861429 398.861429 + 12 7168.0 686.754468 388.772874 384.859062 + 13 7680.0 678.895043 393.846167 386.415087 + 14 8192.0 636.271854 390.095241 374.491442 + 15 8704.0 627.315309 396.763538 380.502740 16 9216.0 604.327881 405.098894 383.002605 - 17 9728.0 585.142883 409.599987 382.427505 - 18 10240.0 563.024047 409.600010 382.803739 - 19 10752.0 546.133312 410.577576 380.601764 - 20 11264.0 531.634232 398.725657 370.831272 + 17 9728.0 585.142883 409.599987 383.369452 + 18 10240.0 564.965524 409.600010 381.911416 + 19 10752.0 546.133312 411.559798 381.445676 + 20 11264.0 531.634232 403.185684 373.908711 21 11776.0 519.052343 409.599991 377.587162 - 22 12288.0 514.680630 413.911572 383.251457 - 23 12800.0 503.194086 410.420828 377.163903 - 24 13312.0 494.180982 408.030638 376.976995 - 25 13824.0 481.882350 412.656711 379.389355 - 26 14336.0 471.967074 399.609753 371.760140 - 27 14848.0 461.297068 405.406157 374.712936 - 28 15360.0 454.269882 406.887417 378.092307 - 29 15872.0 447.098578 407.627589 376.225175 + 22 12288.0 513.336807 413.911572 382.505826 + 23 12800.0 504.433489 410.420828 377.859783 + 24 13312.0 494.180982 404.159395 377.645399 + 25 13824.0 481.882350 411.122660 378.739711 + 26 14336.0 471.967074 400.307157 372.969090 + 27 14848.0 461.297068 404.027214 374.712936 + 28 15360.0 454.269882 406.214870 378.092307 + 29 15872.0 447.098578 405.027112 375.668625 @@ -393,7 +393,7 @@ Layer Normalization .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 5 minutes 40.298 seconds) + **Total running time of the script:** ( 5 minutes 38.066 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 a987247fb..d46ee7134 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 0.083 seconds) + **Total running time of the script:** ( 0 minutes 0.075 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 490652a7f..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 0.249 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 50af5b226..40255b124 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 ================= -**18:18.301** total execution time for **getting-started_tutorials** files: +**17:31.058** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 07:14.455 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:36.741 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:40.298 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:38.066 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:30.958 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:30.839 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:51.976 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:45.313 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.283 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.075 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.249 | 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``) | 00:00.083 | 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 6339899f4..e4cd89a0d 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   15.999999   19.200000
+1        8192.0   19.200000   19.200000
 2       16384.0   38.400001   38.400001
-3       32768.0   76.800002   76.800002
+3       32768.0   63.999998   63.999998
 4       65536.0  127.999995  127.999995
 5      131072.0  219.428568  219.428568
 6      262144.0  341.333321  384.000001
@@ -342,7 +342,7 @@ for different problem sizes.

 15  134217728.0  849.737435  850.656574
-

Total running time of the script: ( 1 minutes 51.976 seconds)

+

Total running time of the script: ( 1 minutes 45.313 seconds)