This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/tvm-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 07aee5ada24 deploying docs
(apache/tvm@c5b8f80be49d458546ab3e2aa6725e8778aeb7af)
07aee5ada24 is described below
commit 07aee5ada24300480ce3501888455dfb2b94e5e9
Author: tvm-bot <[email protected]>
AuthorDate: Mon Oct 19 18:14:34 2026 +0000
deploying docs (apache/tvm@c5b8f80be49d458546ab3e2aa6725e8778aeb7af)
---
.../import_model.zip | Bin 35201 -> 35201 bytes
.../dlight_gpu_scheduling.zip | Bin 26386 -> 26386 bytes
.../11c11e53c7dace51a8be968ee169ed0d/ir_module.zip | Bin 23859 -> 23859 bytes
.../tir_transformation.zip | Bin 16139 -> 16139 bytes
.../meta_schedule.zip | Bin 24279 -> 24279 bytes
.../mix_python_and_tvm_with_pymodule.zip | Bin 38390 -> 38390 bytes
.../relax_creation.zip | Bin 22489 -> 22489 bytes
.../relax_transformation.zip | Bin 11596 -> 11596 bytes
.../optimize_llm.zip | Bin 54486 -> 54486 bytes
.../bring_your_own_codegen.zip | Bin 36585 -> 36585 bytes
.../e2e_opt_model.zip | Bin 14552 -> 14552 bytes
.../quick_start.zip | Bin 16317 -> 16317 bytes
.../export_and_load_executable.zip | Bin 31499 -> 31499 bytes
.../tir_creation.zip | Bin 24695 -> 24695 bytes
.../cross_compilation_and_rpc.zip | Bin 62207 -> 62207 bytes
.../customize_opt.zip | Bin 20750 -> 20750 bytes
.../relax/tutorials/sg_execution_times.rst | 6 ++--
.../tensor_ir/tutorials/sg_execution_times.rst | 10 +++----
.../tensor_ir/tutorials/tir_transformation.rst | 6 ++--
docs/_sources/get_started/tutorials/ir_module.rst | 8 +++---
.../_sources/get_started/tutorials/quick_start.rst | 4 +--
.../get_started/tutorials/sg_execution_times.rst | 6 ++--
.../how_to/tutorials/cross_compilation_and_rpc.rst | 6 ++--
docs/_sources/how_to/tutorials/e2e_opt_model.rst | 2 +-
docs/_sources/how_to/tutorials/optimize_llm.rst | 2 +-
.../how_to/tutorials/sg_execution_times.rst | 16 +++++------
docs/_sources/sg_execution_times.rst | 32 ++++++++++-----------
.../relax/tutorials/sg_execution_times.html | 6 ++--
.../tensor_ir/tutorials/sg_execution_times.html | 10 +++----
.../tensor_ir/tutorials/tir_transformation.html | 6 ++--
docs/get_started/tutorials/ir_module.html | 8 +++---
docs/get_started/tutorials/quick_start.html | 4 +--
docs/get_started/tutorials/sg_execution_times.html | 6 ++--
.../tutorials/cross_compilation_and_rpc.html | 6 ++--
docs/how_to/tutorials/e2e_opt_model.html | 4 +--
docs/how_to/tutorials/optimize_llm.html | 2 +-
docs/how_to/tutorials/sg_execution_times.html | 16 +++++------
docs/reference/api/python/relax/relax.html | 2 +-
docs/searchindex.js | 2 +-
docs/sg_execution_times.html | 32 ++++++++++-----------
40 files changed, 101 insertions(+), 101 deletions(-)
diff --git a/docs/_downloads/050dda7aeddba33e083ae36606d3270f/import_model.zip
b/docs/_downloads/050dda7aeddba33e083ae36606d3270f/import_model.zip
index bbcb939d0d3..a962128f838 100644
Binary files
a/docs/_downloads/050dda7aeddba33e083ae36606d3270f/import_model.zip and
b/docs/_downloads/050dda7aeddba33e083ae36606d3270f/import_model.zip differ
diff --git
a/docs/_downloads/0eec6b3ea6ba863d0ed14b037c4b83ea/dlight_gpu_scheduling.zip
b/docs/_downloads/0eec6b3ea6ba863d0ed14b037c4b83ea/dlight_gpu_scheduling.zip
index 2937ce5e552..f15876b8544 100644
Binary files
a/docs/_downloads/0eec6b3ea6ba863d0ed14b037c4b83ea/dlight_gpu_scheduling.zip
and
b/docs/_downloads/0eec6b3ea6ba863d0ed14b037c4b83ea/dlight_gpu_scheduling.zip
differ
diff --git a/docs/_downloads/11c11e53c7dace51a8be968ee169ed0d/ir_module.zip
b/docs/_downloads/11c11e53c7dace51a8be968ee169ed0d/ir_module.zip
index 4602ef1962e..2474f9e8fab 100644
Binary files a/docs/_downloads/11c11e53c7dace51a8be968ee169ed0d/ir_module.zip
and b/docs/_downloads/11c11e53c7dace51a8be968ee169ed0d/ir_module.zip differ
diff --git
a/docs/_downloads/18ba0d2ee8120824175aaef66bc9c9bf/tir_transformation.zip
b/docs/_downloads/18ba0d2ee8120824175aaef66bc9c9bf/tir_transformation.zip
index a53c9bae425..39a4c36efde 100644
Binary files
a/docs/_downloads/18ba0d2ee8120824175aaef66bc9c9bf/tir_transformation.zip and
b/docs/_downloads/18ba0d2ee8120824175aaef66bc9c9bf/tir_transformation.zip differ
diff --git a/docs/_downloads/249a4acaa182fd00b9c381b53025777d/meta_schedule.zip
b/docs/_downloads/249a4acaa182fd00b9c381b53025777d/meta_schedule.zip
index ee1b0d925fd..18b7640feef 100644
Binary files
a/docs/_downloads/249a4acaa182fd00b9c381b53025777d/meta_schedule.zip and
b/docs/_downloads/249a4acaa182fd00b9c381b53025777d/meta_schedule.zip differ
diff --git
a/docs/_downloads/373278b9f6fc686adeaa0219598fe78b/mix_python_and_tvm_with_pymodule.zip
b/docs/_downloads/373278b9f6fc686adeaa0219598fe78b/mix_python_and_tvm_with_pymodule.zip
index 034e56cfb8b..9aa54e42eee 100644
Binary files
a/docs/_downloads/373278b9f6fc686adeaa0219598fe78b/mix_python_and_tvm_with_pymodule.zip
and
b/docs/_downloads/373278b9f6fc686adeaa0219598fe78b/mix_python_and_tvm_with_pymodule.zip
differ
diff --git
a/docs/_downloads/4753776bbe68e7c9ee4d19117973fc8b/relax_creation.zip
b/docs/_downloads/4753776bbe68e7c9ee4d19117973fc8b/relax_creation.zip
index 3056976b3a8..f395dca5abf 100644
Binary files
a/docs/_downloads/4753776bbe68e7c9ee4d19117973fc8b/relax_creation.zip and
b/docs/_downloads/4753776bbe68e7c9ee4d19117973fc8b/relax_creation.zip differ
diff --git
a/docs/_downloads/7d201684dfa095a5ea48d98e9a2ef7ad/relax_transformation.zip
b/docs/_downloads/7d201684dfa095a5ea48d98e9a2ef7ad/relax_transformation.zip
index 48bc993eed2..32f276026cc 100644
Binary files
a/docs/_downloads/7d201684dfa095a5ea48d98e9a2ef7ad/relax_transformation.zip and
b/docs/_downloads/7d201684dfa095a5ea48d98e9a2ef7ad/relax_transformation.zip
differ
diff --git a/docs/_downloads/83e85f38cf16f1d926d06615fd54095c/optimize_llm.zip
b/docs/_downloads/83e85f38cf16f1d926d06615fd54095c/optimize_llm.zip
index 5724744b2db..87fd971fdec 100644
Binary files
a/docs/_downloads/83e85f38cf16f1d926d06615fd54095c/optimize_llm.zip and
b/docs/_downloads/83e85f38cf16f1d926d06615fd54095c/optimize_llm.zip differ
diff --git
a/docs/_downloads/8c05f1d580979a2c26428a509c07ed72/bring_your_own_codegen.zip
b/docs/_downloads/8c05f1d580979a2c26428a509c07ed72/bring_your_own_codegen.zip
index 01501d0d03c..ce07c979c4a 100644
Binary files
a/docs/_downloads/8c05f1d580979a2c26428a509c07ed72/bring_your_own_codegen.zip
and
b/docs/_downloads/8c05f1d580979a2c26428a509c07ed72/bring_your_own_codegen.zip
differ
diff --git a/docs/_downloads/a7dd7652b2ad50f82d7b739ce3645799/e2e_opt_model.zip
b/docs/_downloads/a7dd7652b2ad50f82d7b739ce3645799/e2e_opt_model.zip
index c4127c579c1..29c380fe270 100644
Binary files
a/docs/_downloads/a7dd7652b2ad50f82d7b739ce3645799/e2e_opt_model.zip and
b/docs/_downloads/a7dd7652b2ad50f82d7b739ce3645799/e2e_opt_model.zip differ
diff --git a/docs/_downloads/bb7db6678496193ed0c55d3b95fa6778/quick_start.zip
b/docs/_downloads/bb7db6678496193ed0c55d3b95fa6778/quick_start.zip
index 5c0d7d415c9..2c1a4aafb57 100644
Binary files a/docs/_downloads/bb7db6678496193ed0c55d3b95fa6778/quick_start.zip
and b/docs/_downloads/bb7db6678496193ed0c55d3b95fa6778/quick_start.zip differ
diff --git
a/docs/_downloads/bc875d02d5382abc9ea5fb9eb2c1de2c/export_and_load_executable.zip
b/docs/_downloads/bc875d02d5382abc9ea5fb9eb2c1de2c/export_and_load_executable.zip
index fa3fd1fc9b2..901801e2f2a 100644
Binary files
a/docs/_downloads/bc875d02d5382abc9ea5fb9eb2c1de2c/export_and_load_executable.zip
and
b/docs/_downloads/bc875d02d5382abc9ea5fb9eb2c1de2c/export_and_load_executable.zip
differ
diff --git a/docs/_downloads/be26483bb70b8468499a01c55e8e866c/tir_creation.zip
b/docs/_downloads/be26483bb70b8468499a01c55e8e866c/tir_creation.zip
index 8a6dc8299a6..e94d9e10c89 100644
Binary files
a/docs/_downloads/be26483bb70b8468499a01c55e8e866c/tir_creation.zip and
b/docs/_downloads/be26483bb70b8468499a01c55e8e866c/tir_creation.zip differ
diff --git
a/docs/_downloads/f69380821f417ef2210f45503d81bded/cross_compilation_and_rpc.zip
b/docs/_downloads/f69380821f417ef2210f45503d81bded/cross_compilation_and_rpc.zip
index 753c97bbe42..a92170e4b8b 100644
Binary files
a/docs/_downloads/f69380821f417ef2210f45503d81bded/cross_compilation_and_rpc.zip
and
b/docs/_downloads/f69380821f417ef2210f45503d81bded/cross_compilation_and_rpc.zip
differ
diff --git a/docs/_downloads/f69433a4a80715725df90d1386679956/customize_opt.zip
b/docs/_downloads/f69433a4a80715725df90d1386679956/customize_opt.zip
index b260938523f..75f87e614d4 100644
Binary files
a/docs/_downloads/f69433a4a80715725df90d1386679956/customize_opt.zip and
b/docs/_downloads/f69433a4a80715725df90d1386679956/customize_opt.zip differ
diff --git a/docs/_sources/deep_dive/relax/tutorials/sg_execution_times.rst
b/docs/_sources/deep_dive/relax/tutorials/sg_execution_times.rst
index f2304973a54..7eff3e15a0c 100644
--- a/docs/_sources/deep_dive/relax/tutorials/sg_execution_times.rst
+++ b/docs/_sources/deep_dive/relax/tutorials/sg_execution_times.rst
@@ -6,7 +6,7 @@
Computation times
=================
-**00:00.232** total execution time for 2 files **from
deep_dive/relax/tutorials**:
+**00:00.181** total execution time for 2 files **from
deep_dive/relax/tutorials**:
.. container::
@@ -33,8 +33,8 @@ Computation times
- Time
- Mem (MB)
* - :ref:`sphx_glr_deep_dive_relax_tutorials_relax_creation.py`
(``relax_creation.py``)
- - 00:00.120
+ - 00:00.095
- 0.0
* - :ref:`sphx_glr_deep_dive_relax_tutorials_relax_transformation.py`
(``relax_transformation.py``)
- - 00:00.111
+ - 00:00.086
- 0.0
diff --git a/docs/_sources/deep_dive/tensor_ir/tutorials/sg_execution_times.rst
b/docs/_sources/deep_dive/tensor_ir/tutorials/sg_execution_times.rst
index 4f54edf4dd4..35548777609 100644
--- a/docs/_sources/deep_dive/tensor_ir/tutorials/sg_execution_times.rst
+++ b/docs/_sources/deep_dive/tensor_ir/tutorials/sg_execution_times.rst
@@ -6,7 +6,7 @@
Computation times
=================
-**00:00.762** total execution time for 4 files **from
deep_dive/tensor_ir/tutorials**:
+**00:00.627** total execution time for 4 files **from
deep_dive/tensor_ir/tutorials**:
.. container::
@@ -33,14 +33,14 @@ Computation times
- Time
- Mem (MB)
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_tir_transformation.py`
(``tir_transformation.py``)
- - 00:00.333
+ - 00:00.281
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_dlight_gpu_scheduling.py`
(``dlight_gpu_scheduling.py``)
- - 00:00.246
+ - 00:00.192
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_tir_creation.py`
(``tir_creation.py``)
- - 00:00.168
+ - 00:00.142
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_meta_schedule.py`
(``meta_schedule.py``)
- - 00:00.015
+ - 00:00.013
- 0.0
diff --git a/docs/_sources/deep_dive/tensor_ir/tutorials/tir_transformation.rst
b/docs/_sources/deep_dive/tensor_ir/tutorials/tir_transformation.rst
index 44e545ef6e0..afc7bd319d4 100644
--- a/docs/_sources/deep_dive/tensor_ir/tutorials/tir_transformation.rst
+++ b/docs/_sources/deep_dive/tensor_ir/tutorials/tir_transformation.rst
@@ -122,7 +122,7 @@ original implementation.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2.7515 2.7515 2.7515 2.7515 0.0000
+ 2.6714 2.6714 2.6714 2.6714 0.0000
@@ -312,7 +312,7 @@ action involves reordering these two loops.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 0.8646 0.8646 0.8646 0.8646 0.0000
+ 0.8579 0.8579 0.8579 0.8579 0.0000
@@ -452,7 +452,7 @@ from the reduction update via the **decompose_reduction**
primitive.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 0.3402 0.3402 0.3402 0.3402 0.0000
+ 0.3518 0.3518 0.3518 0.3518 0.0000
diff --git a/docs/_sources/get_started/tutorials/ir_module.rst
b/docs/_sources/get_started/tutorials/ir_module.rst
index 720d1b98a4a..81b247b7459 100644
--- a/docs/_sources/get_started/tutorials/ir_module.rst
+++ b/docs/_sources/get_started/tutorials/ir_module.rst
@@ -763,8 +763,8 @@ We can deploy the IRModule on CPU by specifying the target
as ``llvm``.
.. code-block:: none
- [[ 0.06151915 -0.40003446 0.13588637 0.19235659 0.20258091 0.10505539
- 0.07409582 -0.05737962 0.14458896 -0.05025715]]
+ [[-0.18787932 0.12859452 0.00581972 -0.05709402 -0.06822725 0.3566087
+ -0.08635934 -0.13391502 -0.07908424 0.15001678]]
@@ -830,8 +830,8 @@ Now we can compile the IRModule on GPU, the similar way as
we did on CPU.
.. code-block:: none
- [[ 0.06151911 -0.40003443 0.13588642 0.19235651 0.2025809 0.10505548
- 0.07409582 -0.05737959 0.1445889 -0.05025716]]
+ [[-0.1878793 0.12859447 0.00581972 -0.05709399 -0.06822731 0.35660875
+ -0.08635935 -0.13391498 -0.0790843 0.15001673]]
diff --git a/docs/_sources/get_started/tutorials/quick_start.rst
b/docs/_sources/get_started/tutorials/quick_start.rst
index d536cea6a09..67ac8365c29 100644
--- a/docs/_sources/get_started/tutorials/quick_start.rst
+++ b/docs/_sources/get_started/tutorials/quick_start.rst
@@ -227,8 +227,8 @@ different devices.
.. code-block:: none
- [[25577.135 25550.11 25236.436 25150.656 25420.518 26848.246 24796.855
- 26814.506 25042.994 25128.121]]
+ [[23923.15 25373.387 24548.17 24347.828 25432.965 25338.299 26389.438
+ 25616.996 26094.936 24019.744]]
diff --git a/docs/_sources/get_started/tutorials/sg_execution_times.rst
b/docs/_sources/get_started/tutorials/sg_execution_times.rst
index 52156ac5c76..40139f784cf 100644
--- a/docs/_sources/get_started/tutorials/sg_execution_times.rst
+++ b/docs/_sources/get_started/tutorials/sg_execution_times.rst
@@ -6,7 +6,7 @@
Computation times
=================
-**00:05.297** total execution time for 2 files **from get_started/tutorials**:
+**00:04.494** total execution time for 2 files **from get_started/tutorials**:
.. container::
@@ -33,8 +33,8 @@ Computation times
- Time
- Mem (MB)
* - :ref:`sphx_glr_get_started_tutorials_ir_module.py` (``ir_module.py``)
- - 00:05.080
+ - 00:04.314
- 0.0
* - :ref:`sphx_glr_get_started_tutorials_quick_start.py`
(``quick_start.py``)
- - 00:00.217
+ - 00:00.180
- 0.0
diff --git a/docs/_sources/how_to/tutorials/cross_compilation_and_rpc.rst
b/docs/_sources/how_to/tutorials/cross_compilation_and_rpc.rst
index fd2ac443b82..81faa44366f 100644
--- a/docs/_sources/how_to/tutorials/cross_compilation_and_rpc.rst
+++ b/docs/_sources/how_to/tutorials/cross_compilation_and_rpc.rst
@@ -276,7 +276,7 @@ device and returns the measured cost. Network overhead is
excluded.
.. code-block:: none
- 1.07e-07 secs/op
+ 9.4e-08 secs/op
@@ -861,8 +861,8 @@ This workflow is applicable to various deployment scenarios:
Converted PyTorch model to Relax:
- Number of parameters: 4
Using local target for demonstration
- Exported library to: /tmp/tmp2uos0fh2/model_deployed.so
- Saved parameters to: /tmp/tmp2uos0fh2/model_params.npz
+ Exported library to: /tmp/tmp6zn6kdt_/model_deployed.so
+ Saved parameters to: /tmp/tmp6zn6kdt_/model_params.npz
RPC workflow (works for any remote device):
==================================================
diff --git a/docs/_sources/how_to/tutorials/e2e_opt_model.rst
b/docs/_sources/how_to/tutorials/e2e_opt_model.rst
index 595a3b33b18..16acf41c878 100644
--- a/docs/_sources/how_to/tutorials/e2e_opt_model.rst
+++ b/docs/_sources/how_to/tutorials/e2e_opt_model.rst
@@ -54,7 +54,7 @@ PyTorch.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth";
to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
- 0%| | 0.00/44.7M [00:00<?, ?B/s] 66%|██████▋ |
29.6M/44.7M [00:00<00:00, 310MB/s] 100%|██████████| 44.7M/44.7M
[00:00<00:00, 337MB/s]
+ 0%| | 0.00/44.7M [00:00<?, ?B/s] 72%|███████▏ |
32.2M/44.7M [00:00<00:00, 338MB/s] 100%|██████████| 44.7M/44.7M
[00:00<00:00, 364MB/s]
diff --git a/docs/_sources/how_to/tutorials/optimize_llm.rst
b/docs/_sources/how_to/tutorials/optimize_llm.rst
index d14c0eb32df..be93d3bfeb4 100644
--- a/docs/_sources/how_to/tutorials/optimize_llm.rst
+++ b/docs/_sources/how_to/tutorials/optimize_llm.rst
@@ -862,7 +862,7 @@ IRModule to generate the token.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** (5 minutes 33.447 seconds)
+ **Total running time of the script:** (2 minutes 49.530 seconds)
.. _sphx_glr_download_how_to_tutorials_optimize_llm.py:
diff --git a/docs/_sources/how_to/tutorials/sg_execution_times.rst
b/docs/_sources/how_to/tutorials/sg_execution_times.rst
index 1357b29b057..a577a8980d7 100644
--- a/docs/_sources/how_to/tutorials/sg_execution_times.rst
+++ b/docs/_sources/how_to/tutorials/sg_execution_times.rst
@@ -6,7 +6,7 @@
Computation times
=================
-**05:39.027** total execution time for 8 files **from how_to/tutorials**:
+**02:54.423** total execution time for 8 files **from how_to/tutorials**:
.. container::
@@ -33,25 +33,25 @@ Computation times
- Time
- Mem (MB)
* - :ref:`sphx_glr_how_to_tutorials_optimize_llm.py` (``optimize_llm.py``)
- - 05:33.447
+ - 02:49.530
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_import_model.py` (``import_model.py``)
- - 00:03.726
+ - 00:03.381
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_e2e_opt_model.py` (``e2e_opt_model.py``)
- - 00:00.737
+ - 00:00.582
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_cross_compilation_and_rpc.py`
(``cross_compilation_and_rpc.py``)
- - 00:00.607
+ - 00:00.498
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_customize_opt.py` (``customize_opt.py``)
- - 00:00.373
+ - 00:00.311
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_bring_your_own_codegen.py`
(``bring_your_own_codegen.py``)
- - 00:00.129
+ - 00:00.115
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_mix_python_and_tvm_with_pymodule.py`
(``mix_python_and_tvm_with_pymodule.py``)
- - 00:00.005
+ - 00:00.004
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_export_and_load_executable.py`
(``export_and_load_executable.py``)
- 00:00.002
diff --git a/docs/_sources/sg_execution_times.rst
b/docs/_sources/sg_execution_times.rst
index 67413c6a8a7..2a1f0146be6 100644
--- a/docs/_sources/sg_execution_times.rst
+++ b/docs/_sources/sg_execution_times.rst
@@ -6,7 +6,7 @@
Computation times
=================
-**05:45.317** total execution time for 16 files **from all galleries**:
+**02:59.725** total execution time for 16 files **from all galleries**:
.. container::
@@ -33,49 +33,49 @@ Computation times
- Time
- Mem (MB)
* - :ref:`sphx_glr_how_to_tutorials_optimize_llm.py`
(``../how_to/tutorials/optimize_llm.py``)
- - 05:33.447
+ - 02:49.530
- 0.0
* - :ref:`sphx_glr_get_started_tutorials_ir_module.py`
(``../get_started/tutorials/ir_module.py``)
- - 00:05.080
+ - 00:04.314
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_import_model.py`
(``../how_to/tutorials/import_model.py``)
- - 00:03.726
+ - 00:03.381
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_e2e_opt_model.py`
(``../how_to/tutorials/e2e_opt_model.py``)
- - 00:00.737
+ - 00:00.582
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_cross_compilation_and_rpc.py`
(``../how_to/tutorials/cross_compilation_and_rpc.py``)
- - 00:00.607
+ - 00:00.498
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_customize_opt.py`
(``../how_to/tutorials/customize_opt.py``)
- - 00:00.373
+ - 00:00.311
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_tir_transformation.py`
(``../deep_dive/tensor_ir/tutorials/tir_transformation.py``)
- - 00:00.333
+ - 00:00.281
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_dlight_gpu_scheduling.py`
(``../deep_dive/tensor_ir/tutorials/dlight_gpu_scheduling.py``)
- - 00:00.246
+ - 00:00.192
- 0.0
* - :ref:`sphx_glr_get_started_tutorials_quick_start.py`
(``../get_started/tutorials/quick_start.py``)
- - 00:00.217
+ - 00:00.180
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_tir_creation.py`
(``../deep_dive/tensor_ir/tutorials/tir_creation.py``)
- - 00:00.168
+ - 00:00.142
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_bring_your_own_codegen.py`
(``../how_to/tutorials/bring_your_own_codegen.py``)
- - 00:00.129
+ - 00:00.115
- 0.0
* - :ref:`sphx_glr_deep_dive_relax_tutorials_relax_creation.py`
(``../deep_dive/relax/tutorials/relax_creation.py``)
- - 00:00.120
+ - 00:00.095
- 0.0
* - :ref:`sphx_glr_deep_dive_relax_tutorials_relax_transformation.py`
(``../deep_dive/relax/tutorials/relax_transformation.py``)
- - 00:00.111
+ - 00:00.086
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_meta_schedule.py`
(``../deep_dive/tensor_ir/tutorials/meta_schedule.py``)
- - 00:00.015
+ - 00:00.013
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_mix_python_and_tvm_with_pymodule.py`
(``../how_to/tutorials/mix_python_and_tvm_with_pymodule.py``)
- - 00:00.005
+ - 00:00.004
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_export_and_load_executable.py`
(``../how_to/tutorials/export_and_load_executable.py``)
- 00:00.002
diff --git a/docs/deep_dive/relax/tutorials/sg_execution_times.html
b/docs/deep_dive/relax/tutorials/sg_execution_times.html
index 4d1f1ce3bdf..fd73a76bb8c 100644
--- a/docs/deep_dive/relax/tutorials/sg_execution_times.html
+++ b/docs/deep_dive/relax/tutorials/sg_execution_times.html
@@ -630,7 +630,7 @@ document.write(`
<section id="computation-times">
<span
id="sphx-glr-deep-dive-relax-tutorials-sg-execution-times"></span><h1>Computation
times<a class="headerlink" href="#computation-times" title="Link to this
heading">#</a></h1>
-<p><strong>00:00.232</strong> total execution time for 2 files <strong>from
deep_dive/relax/tutorials</strong>:</p>
+<p><strong>00:00.181</strong> total execution time for 2 files <strong>from
deep_dive/relax/tutorials</strong>:</p>
<div class="docutils container">
<style scoped>
<link
href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css";
rel="stylesheet" />
@@ -652,11 +652,11 @@ $(document).ready( function () {
</thead>
<tbody>
<tr class="row-even"><td><p><a class="reference internal"
href="relax_creation.html#sphx-glr-deep-dive-relax-tutorials-relax-creation-py"><span
class="std std-ref">Relax Creation</span></a> (<code class="docutils literal
notranslate"><span class="pre">relax_creation.py</span></code>)</p></td>
-<td><p>00:00.120</p></td>
+<td><p>00:00.095</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="relax_transformation.html#sphx-glr-deep-dive-relax-tutorials-relax-transformation-py"><span
class="std std-ref">Transformation</span></a> (<code class="docutils literal
notranslate"><span class="pre">relax_transformation.py</span></code>)</p></td>
-<td><p>00:00.111</p></td>
+<td><p>00:00.086</p></td>
<td><p>0.0</p></td>
</tr>
</tbody>
diff --git a/docs/deep_dive/tensor_ir/tutorials/sg_execution_times.html
b/docs/deep_dive/tensor_ir/tutorials/sg_execution_times.html
index cd033b49e18..531b5700585 100644
--- a/docs/deep_dive/tensor_ir/tutorials/sg_execution_times.html
+++ b/docs/deep_dive/tensor_ir/tutorials/sg_execution_times.html
@@ -630,7 +630,7 @@ document.write(`
<section id="computation-times">
<span
id="sphx-glr-deep-dive-tensor-ir-tutorials-sg-execution-times"></span><h1>Computation
times<a class="headerlink" href="#computation-times" title="Link to this
heading">#</a></h1>
-<p><strong>00:00.762</strong> total execution time for 4 files <strong>from
deep_dive/tensor_ir/tutorials</strong>:</p>
+<p><strong>00:00.627</strong> total execution time for 4 files <strong>from
deep_dive/tensor_ir/tutorials</strong>:</p>
<div class="docutils container">
<style scoped>
<link
href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css";
rel="stylesheet" />
@@ -652,19 +652,19 @@ $(document).ready( function () {
</thead>
<tbody>
<tr class="row-even"><td><p><a class="reference internal"
href="tir_transformation.html#sphx-glr-deep-dive-tensor-ir-tutorials-tir-transformation-py"><span
class="std std-ref">Transformation</span></a> (<code class="docutils literal
notranslate"><span class="pre">tir_transformation.py</span></code>)</p></td>
-<td><p>00:00.333</p></td>
+<td><p>00:00.281</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="dlight_gpu_scheduling.html#sphx-glr-deep-dive-tensor-ir-tutorials-dlight-gpu-scheduling-py"><span
class="std std-ref">DLight: Rule-Based GPU Scheduling</span></a> (<code
class="docutils literal notranslate"><span
class="pre">dlight_gpu_scheduling.py</span></code>)</p></td>
-<td><p>00:00.246</p></td>
+<td><p>00:00.192</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="tir_creation.html#sphx-glr-deep-dive-tensor-ir-tutorials-tir-creation-py"><span
class="std std-ref">TensorIR Creation</span></a> (<code class="docutils
literal notranslate"><span class="pre">tir_creation.py</span></code>)</p></td>
-<td><p>00:00.168</p></td>
+<td><p>00:00.142</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="meta_schedule.html#sphx-glr-deep-dive-tensor-ir-tutorials-meta-schedule-py"><span
class="std std-ref">MetaSchedule: Search-Based Auto-Tuning</span></a> (<code
class="docutils literal notranslate"><span
class="pre">meta_schedule.py</span></code>)</p></td>
-<td><p>00:00.015</p></td>
+<td><p>00:00.013</p></td>
<td><p>0.0</p></td>
</tr>
</tbody>
diff --git a/docs/deep_dive/tensor_ir/tutorials/tir_transformation.html
b/docs/deep_dive/tensor_ir/tutorials/tir_transformation.html
index 3f33b41df58..473fb2e4506 100644
--- a/docs/deep_dive/tensor_ir/tutorials/tir_transformation.html
+++ b/docs/deep_dive/tensor_ir/tutorials/tir_transformation.html
@@ -719,7 +719,7 @@ original implementation.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2.7515 2.7515 2.7515 2.7515 0.0000
+ 2.6714 2.6714 2.6714 2.6714 0.0000
</pre></div>
</div>
<section id="initialization-schedule">
@@ -833,7 +833,7 @@ class Module:
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 0.8646 0.8646 0.8646 0.8646 0.0000
+ 0.8579 0.8579 0.8579 0.8579 0.0000
</pre></div>
</div>
</section>
@@ -939,7 +939,7 @@ class Module:
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 0.3402 0.3402 0.3402 0.3402 0.0000
+ 0.3518 0.3518 0.3518 0.3518 0.0000
</pre></div>
</div>
</section>
diff --git a/docs/get_started/tutorials/ir_module.html
b/docs/get_started/tutorials/ir_module.html
index 100da63868c..29d6b560fce 100644
--- a/docs/get_started/tutorials/ir_module.html
+++ b/docs/get_started/tutorials/ir_module.html
@@ -1224,8 +1224,8 @@ backends.</p>
<span class="nb">print</span><span class="p">(</span><span
class="n">cpu_out</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[ 0.06151915 -0.40003446 0.13588637
0.19235659 0.20258091 0.10505539
- 0.07409582 -0.05737962 0.14458896 -0.05025715]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[-0.18787932 0.12859452 0.00581972
-0.05709402 -0.06822725 0.3566087
+ -0.08635934 -0.13391502 -0.07908424 0.15001678]]
</pre></div>
</div>
</section>
@@ -1259,8 +1259,8 @@ the details of <code class="docutils literal
notranslate"><span class="pre">DLig
<span class="k">assert</span> <span class="n">np</span><span
class="o">.</span><span class="n">allclose</span><span class="p">(</span><span
class="n">cpu_out</span><span class="p">,</span> <span
class="n">gpu_out</span><span class="p">,</span> <span
class="n">atol</span><span class="o">=</span><span class="mf">1e-3</span><span
class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[ 0.06151911 -0.40003443 0.13588642
0.19235651 0.2025809 0.10505548
- 0.07409582 -0.05737959 0.1445889 -0.05025716]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[-0.1878793 0.12859447 0.00581972
-0.05709399 -0.06822731 0.35660875
+ -0.08635935 -0.13391498 -0.0790843 0.15001673]]
</pre></div>
</div>
</section>
diff --git a/docs/get_started/tutorials/quick_start.html
b/docs/get_started/tutorials/quick_start.html
index 00038a911b7..0f0c73d8334 100644
--- a/docs/get_started/tutorials/quick_start.html
+++ b/docs/get_started/tutorials/quick_start.html
@@ -801,8 +801,8 @@ different devices.</p>
<span class="nb">print</span><span class="p">(</span><span
class="n">vm</span><span class="p">[</span><span
class="s2">"forward"</span><span class="p">](</span><span
class="n">tvm_data</span><span class="p">,</span> <span class="o">*</span><a
href="https://docs.python.org/3/builtins/stdtypes.html#list";
title="builtins.list" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">params</span></a><span class="p">)</span>< [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[25577.135 25550.11 25236.436 25150.656
25420.518 26848.246 24796.855
- 26814.506 25042.994 25128.121]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[23923.15 25373.387 24548.17 24347.828
25432.965 25338.299 26389.438
+ 25616.996 26094.936 24019.744]]
</pre></div>
</div>
<p>Our goal is to bring machine learning to the application with any language
of interest,
diff --git a/docs/get_started/tutorials/sg_execution_times.html
b/docs/get_started/tutorials/sg_execution_times.html
index ec59c9d557f..9afeb172759 100644
--- a/docs/get_started/tutorials/sg_execution_times.html
+++ b/docs/get_started/tutorials/sg_execution_times.html
@@ -630,7 +630,7 @@ document.write(`
<section id="computation-times">
<span
id="sphx-glr-get-started-tutorials-sg-execution-times"></span><h1>Computation
times<a class="headerlink" href="#computation-times" title="Link to this
heading">#</a></h1>
-<p><strong>00:05.297</strong> total execution time for 2 files <strong>from
get_started/tutorials</strong>:</p>
+<p><strong>00:04.494</strong> total execution time for 2 files <strong>from
get_started/tutorials</strong>:</p>
<div class="docutils container">
<style scoped>
<link
href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css";
rel="stylesheet" />
@@ -652,11 +652,11 @@ $(document).ready( function () {
</thead>
<tbody>
<tr class="row-even"><td><p><a class="reference internal"
href="ir_module.html#sphx-glr-get-started-tutorials-ir-module-py"><span
class="std std-ref">IRModule</span></a> (<code class="docutils literal
notranslate"><span class="pre">ir_module.py</span></code>)</p></td>
-<td><p>00:05.080</p></td>
+<td><p>00:04.314</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="quick_start.html#sphx-glr-get-started-tutorials-quick-start-py"><span
class="std std-ref">Quick Start</span></a> (<code class="docutils literal
notranslate"><span class="pre">quick_start.py</span></code>)</p></td>
-<td><p>00:00.217</p></td>
+<td><p>00:00.180</p></td>
<td><p>0.0</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tutorials/cross_compilation_and_rpc.html
b/docs/how_to/tutorials/cross_compilation_and_rpc.html
index dcf2ff5202d..7c59a1850d0 100644
--- a/docs/how_to/tutorials/cross_compilation_and_rpc.html
+++ b/docs/how_to/tutorials/cross_compilation_and_rpc.html
@@ -830,7 +830,7 @@ device and returns the measured cost. Network overhead is
excluded.</p>
<span class="nb">print</span><span class="p">(</span><span
class="sa">f</span><span class="s2">"</span><span class="si">{</span><span
class="n">cost</span><span class="si">:</span><span class="s2">g</span><span
class="si">}</span><span class="s2"> secs/op"</span><span
class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>1.07e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>9.4e-08 secs/op
</pre></div>
</div>
</section>
@@ -1355,8 +1355,8 @@ for ONNX models. Simply replace <code class="docutils
literal notranslate"><span
Converted PyTorch model to Relax:
- Number of parameters: 4
Using local target for demonstration
-Exported library to: /tmp/tmp2uos0fh2/model_deployed.so
-Saved parameters to: /tmp/tmp2uos0fh2/model_params.npz
+Exported library to: /tmp/tmp6zn6kdt_/model_deployed.so
+Saved parameters to: /tmp/tmp6zn6kdt_/model_params.npz
RPC workflow (works for any remote device):
==================================================
diff --git a/docs/how_to/tutorials/e2e_opt_model.html
b/docs/how_to/tutorials/e2e_opt_model.html
index c98c68b6978..31597b77199 100644
--- a/docs/how_to/tutorials/e2e_opt_model.html
+++ b/docs/how_to/tutorials/e2e_opt_model.html
@@ -670,8 +670,8 @@ PyTorch.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>Downloading:
"https://download.pytorch.org/models/resnet18-f37072fd.pth" to
/workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 66%|██████▋ | 29.6M/44.7M [00:00<00:00, 310MB/s]
-100%|██████████| 44.7M/44.7M [00:00<00:00, 337MB/s]
+ 72%|███████▏ | 32.2M/44.7M [00:00<00:00, 338MB/s]
+100%|██████████| 44.7M/44.7M [00:00<00:00, 364MB/s]
</pre></div>
</div>
</section>
diff --git a/docs/how_to/tutorials/optimize_llm.html
b/docs/how_to/tutorials/optimize_llm.html
index a1fda6a0559..82138bb8372 100644
--- a/docs/how_to/tutorials/optimize_llm.html
+++ b/docs/how_to/tutorials/optimize_llm.html
@@ -1249,7 +1249,7 @@ IRModule to generate the token.</p>
<span class="nb">print</span><span class="p">(</span><span
class="n">tokenizer</span><span class="o">.</span><span
class="n">decode</span><span class="p">(</span><span
class="n">output_tokens</span><span class="p">))</span>
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong>
(5 minutes 33.447 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong>
(2 minutes 49.530 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container"
id="sphx-glr-download-how-to-tutorials-optimize-llm-py">
<div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
<p><a class="reference download internal" download=""
href="../../_downloads/ab03cb35cd7f92b5425a8974fcab921a/optimize_llm.ipynb"><code
class="xref download docutils literal notranslate"><span
class="pre">Download</span> <span class="pre">Jupyter</span> <span
class="pre">notebook:</span> <span
class="pre">optimize_llm.ipynb</span></code></a></p>
diff --git a/docs/how_to/tutorials/sg_execution_times.html
b/docs/how_to/tutorials/sg_execution_times.html
index 46b6ffe7c46..5f0b9cfb863 100644
--- a/docs/how_to/tutorials/sg_execution_times.html
+++ b/docs/how_to/tutorials/sg_execution_times.html
@@ -630,7 +630,7 @@ document.write(`
<section id="computation-times">
<span id="sphx-glr-how-to-tutorials-sg-execution-times"></span><h1>Computation
times<a class="headerlink" href="#computation-times" title="Link to this
heading">#</a></h1>
-<p><strong>05:39.027</strong> total execution time for 8 files <strong>from
how_to/tutorials</strong>:</p>
+<p><strong>02:54.423</strong> total execution time for 8 files <strong>from
how_to/tutorials</strong>:</p>
<div class="docutils container">
<style scoped>
<link
href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css";
rel="stylesheet" />
@@ -652,31 +652,31 @@ $(document).ready( function () {
</thead>
<tbody>
<tr class="row-even"><td><p><a class="reference internal"
href="optimize_llm.html#sphx-glr-how-to-tutorials-optimize-llm-py"><span
class="std std-ref">Optimize Large Language Model</span></a> (<code
class="docutils literal notranslate"><span
class="pre">optimize_llm.py</span></code>)</p></td>
-<td><p>05:33.447</p></td>
+<td><p>02:49.530</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="import_model.html#sphx-glr-how-to-tutorials-import-model-py"><span
class="std std-ref">Importing Models from ML Frameworks</span></a> (<code
class="docutils literal notranslate"><span
class="pre">import_model.py</span></code>)</p></td>
-<td><p>00:03.726</p></td>
+<td><p>00:03.381</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="e2e_opt_model.html#sphx-glr-how-to-tutorials-e2e-opt-model-py"><span
class="std std-ref">End-to-End Optimize Model</span></a> (<code class="docutils
literal notranslate"><span class="pre">e2e_opt_model.py</span></code>)</p></td>
-<td><p>00:00.737</p></td>
+<td><p>00:00.582</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="cross_compilation_and_rpc.html#sphx-glr-how-to-tutorials-cross-compilation-and-rpc-py"><span
class="std std-ref">Cross Compilation and RPC</span></a> (<code
class="docutils literal notranslate"><span
class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.607</p></td>
+<td><p>00:00.498</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="customize_opt.html#sphx-glr-how-to-tutorials-customize-opt-py"><span
class="std std-ref">Customize Optimization</span></a> (<code class="docutils
literal notranslate"><span class="pre">customize_opt.py</span></code>)</p></td>
-<td><p>00:00.373</p></td>
+<td><p>00:00.311</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="bring_your_own_codegen.html#sphx-glr-how-to-tutorials-bring-your-own-codegen-py"><span
class="std std-ref">Bring Your Own Codegen</span></a> (<code class="docutils
literal notranslate"><span
class="pre">bring_your_own_codegen.py</span></code>)</p></td>
-<td><p>00:00.129</p></td>
+<td><p>00:00.115</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="mix_python_and_tvm_with_pymodule.html#sphx-glr-how-to-tutorials-mix-python-and-tvm-with-pymodule-py"><span
class="std std-ref">Mix Python/PyTorch with TVM Using BasePyModule</span></a>
(<code class="docutils literal notranslate"><span
class="pre">mix_python_and_tvm_with_pymodule.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.004</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="export_and_load_executable.html#sphx-glr-how-to-tutorials-export-and-load-executable-py"><span
class="std std-ref">Export and Load Relax Executables</span></a> (<code
class="docutils literal notranslate"><span
class="pre">export_and_load_executable.py</span></code>)</p></td>
diff --git a/docs/reference/api/python/relax/relax.html
b/docs/reference/api/python/relax/relax.html
index 6bdfc301dee..906d70b0b20 100644
--- a/docs/reference/api/python/relax/relax.html
+++ b/docs/reference/api/python/relax/relax.html
@@ -2427,7 +2427,7 @@ Python functions stored in the IRModule’s pyfuncs
attribute.</p>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.relax.build">
-<span class="sig-prename descclassname"><span
class="pre">tvm.relax.</span></span><span class="sig-name descname"><span
class="pre">build</span></span><span class="sig-paren">(</span><em
class="sig-param"><span class="n"><span class="pre">mod</span></span><span
class="p"><span class="pre">:</span></span><span class="w"> </span><span
class="n"><a class="reference internal" href="../ir.html#tvm_tirx.ir.IRModule"
title="tvm_tirx.ir.module.IRModule"><span class="pre">IRModule</span></a></spa
[...]
+<span class="sig-prename descclassname"><span
class="pre">tvm.relax.</span></span><span class="sig-name descname"><span
class="pre">build</span></span><span class="sig-paren">(</span><em
class="sig-param"><span class="n"><span class="pre">mod</span></span><span
class="p"><span class="pre">:</span></span><span class="w"> </span><span
class="n"><a class="reference internal" href="../ir.html#tvm_tirx.ir.IRModule"
title="tvm_tirx.ir.module.IRModule"><span class="pre">IRModule</span></a></spa
[...]
<dd><p>Build an IRModule to VM executable.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 781b7a2a4ae..bef723c1572 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"128-bit global load": [[127,
"bit-global-load"]], "@Tx.function vs @Tx.jit": [[136,
"tx-function-vs-tx-jit"]], "@Tx.inline \u2014 inline functions": [[137,
"tx-inline-inline-functions"]], "@Tx.meta_class \u2014 parser-side state
objects": [[137, "tx-meta-class-parser-side-state-objects"]], "A stable
extension boundary for future hardware": [[141,
"a-stable-extension-boundary-for-future-hardware"]], "A worked example": [[125,
"a-worked-example"]], "API Refe [...]
\ No newline at end of file
+Search.setIndex({"alltitles": {"128-bit global load": [[127,
"bit-global-load"]], "@Tx.function vs @Tx.jit": [[136,
"tx-function-vs-tx-jit"]], "@Tx.inline \u2014 inline functions": [[137,
"tx-inline-inline-functions"]], "@Tx.meta_class \u2014 parser-side state
objects": [[137, "tx-meta-class-parser-side-state-objects"]], "A stable
extension boundary for future hardware": [[141,
"a-stable-extension-boundary-for-future-hardware"]], "A worked example": [[125,
"a-worked-example"]], "API Refe [...]
\ No newline at end of file
diff --git a/docs/sg_execution_times.html b/docs/sg_execution_times.html
index b4b13882ff6..ba569dfbe81 100644
--- a/docs/sg_execution_times.html
+++ b/docs/sg_execution_times.html
@@ -630,7 +630,7 @@ document.write(`
<section id="computation-times">
<span id="sphx-glr-sg-execution-times"></span><h1>Computation times<a
class="headerlink" href="#computation-times" title="Link to this
heading">#</a></h1>
-<p><strong>05:45.317</strong> total execution time for 16 files <strong>from
all galleries</strong>:</p>
+<p><strong>02:59.725</strong> total execution time for 16 files <strong>from
all galleries</strong>:</p>
<div class="docutils container">
<style scoped>
<link
href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css";
rel="stylesheet" />
@@ -652,63 +652,63 @@ $(document).ready( function () {
</thead>
<tbody>
<tr class="row-even"><td><p><a class="reference internal"
href="how_to/tutorials/optimize_llm.html#sphx-glr-how-to-tutorials-optimize-llm-py"><span
class="std std-ref">Optimize Large Language Model</span></a> (<code
class="docutils literal notranslate"><span
class="pre">../how_to/tutorials/optimize_llm.py</span></code>)</p></td>
-<td><p>05:33.447</p></td>
+<td><p>02:49.530</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="get_started/tutorials/ir_module.html#sphx-glr-get-started-tutorials-ir-module-py"><span
class="std std-ref">IRModule</span></a> (<code class="docutils literal
notranslate"><span
class="pre">../get_started/tutorials/ir_module.py</span></code>)</p></td>
-<td><p>00:05.080</p></td>
+<td><p>00:04.314</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="how_to/tutorials/import_model.html#sphx-glr-how-to-tutorials-import-model-py"><span
class="std std-ref">Importing Models from ML Frameworks</span></a> (<code
class="docutils literal notranslate"><span
class="pre">../how_to/tutorials/import_model.py</span></code>)</p></td>
-<td><p>00:03.726</p></td>
+<td><p>00:03.381</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="how_to/tutorials/e2e_opt_model.html#sphx-glr-how-to-tutorials-e2e-opt-model-py"><span
class="std std-ref">End-to-End Optimize Model</span></a> (<code
class="docutils literal notranslate"><span
class="pre">../how_to/tutorials/e2e_opt_model.py</span></code>)</p></td>
-<td><p>00:00.737</p></td>
+<td><p>00:00.582</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="how_to/tutorials/cross_compilation_and_rpc.html#sphx-glr-how-to-tutorials-cross-compilation-and-rpc-py"><span
class="std std-ref">Cross Compilation and RPC</span></a> (<code
class="docutils literal notranslate"><span
class="pre">../how_to/tutorials/cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.607</p></td>
+<td><p>00:00.498</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="how_to/tutorials/customize_opt.html#sphx-glr-how-to-tutorials-customize-opt-py"><span
class="std std-ref">Customize Optimization</span></a> (<code class="docutils
literal notranslate"><span
class="pre">../how_to/tutorials/customize_opt.py</span></code>)</p></td>
-<td><p>00:00.373</p></td>
+<td><p>00:00.311</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="deep_dive/tensor_ir/tutorials/tir_transformation.html#sphx-glr-deep-dive-tensor-ir-tutorials-tir-transformation-py"><span
class="std std-ref">Transformation</span></a> (<code class="docutils literal
notranslate"><span
class="pre">../deep_dive/tensor_ir/tutorials/tir_transformation.py</span></code>)</p></td>
-<td><p>00:00.333</p></td>
+<td><p>00:00.281</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="deep_dive/tensor_ir/tutorials/dlight_gpu_scheduling.html#sphx-glr-deep-dive-tensor-ir-tutorials-dlight-gpu-scheduling-py"><span
class="std std-ref">DLight: Rule-Based GPU Scheduling</span></a> (<code
class="docutils literal notranslate"><span
class="pre">../deep_dive/tensor_ir/tutorials/dlight_gpu_scheduling.py</span></code>)</p></td>
-<td><p>00:00.246</p></td>
+<td><p>00:00.192</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="get_started/tutorials/quick_start.html#sphx-glr-get-started-tutorials-quick-start-py"><span
class="std std-ref">Quick Start</span></a> (<code class="docutils literal
notranslate"><span
class="pre">../get_started/tutorials/quick_start.py</span></code>)</p></td>
-<td><p>00:00.217</p></td>
+<td><p>00:00.180</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="deep_dive/tensor_ir/tutorials/tir_creation.html#sphx-glr-deep-dive-tensor-ir-tutorials-tir-creation-py"><span
class="std std-ref">TensorIR Creation</span></a> (<code class="docutils
literal notranslate"><span
class="pre">../deep_dive/tensor_ir/tutorials/tir_creation.py</span></code>)</p></td>
-<td><p>00:00.168</p></td>
+<td><p>00:00.142</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="how_to/tutorials/bring_your_own_codegen.html#sphx-glr-how-to-tutorials-bring-your-own-codegen-py"><span
class="std std-ref">Bring Your Own Codegen</span></a> (<code class="docutils
literal notranslate"><span
class="pre">../how_to/tutorials/bring_your_own_codegen.py</span></code>)</p></td>
-<td><p>00:00.129</p></td>
+<td><p>00:00.115</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="deep_dive/relax/tutorials/relax_creation.html#sphx-glr-deep-dive-relax-tutorials-relax-creation-py"><span
class="std std-ref">Relax Creation</span></a> (<code class="docutils literal
notranslate"><span
class="pre">../deep_dive/relax/tutorials/relax_creation.py</span></code>)</p></td>
-<td><p>00:00.120</p></td>
+<td><p>00:00.095</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="deep_dive/relax/tutorials/relax_transformation.html#sphx-glr-deep-dive-relax-tutorials-relax-transformation-py"><span
class="std std-ref">Transformation</span></a> (<code class="docutils literal
notranslate"><span
class="pre">../deep_dive/relax/tutorials/relax_transformation.py</span></code>)</p></td>
-<td><p>00:00.111</p></td>
+<td><p>00:00.086</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="deep_dive/tensor_ir/tutorials/meta_schedule.html#sphx-glr-deep-dive-tensor-ir-tutorials-meta-schedule-py"><span
class="std std-ref">MetaSchedule: Search-Based Auto-Tuning</span></a> (<code
class="docutils literal notranslate"><span
class="pre">../deep_dive/tensor_ir/tutorials/meta_schedule.py</span></code>)</p></td>
-<td><p>00:00.015</p></td>
+<td><p>00:00.013</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal"
href="how_to/tutorials/mix_python_and_tvm_with_pymodule.html#sphx-glr-how-to-tutorials-mix-python-and-tvm-with-pymodule-py"><span
class="std std-ref">Mix Python/PyTorch with TVM Using BasePyModule</span></a>
(<code class="docutils literal notranslate"><span
class="pre">../how_to/tutorials/mix_python_and_tvm_with_pymodule.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.004</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal"
href="how_to/tutorials/export_and_load_executable.html#sphx-glr-how-to-tutorials-export-and-load-executable-py"><span
class="std std-ref">Export and Load Relax Executables</span></a> (<code
class="docutils literal notranslate"><span
class="pre">../how_to/tutorials/export_and_load_executable.py</span></code>)</p></td>
