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 3cc9e98506d deploying docs
(apache/tvm@d4633957069120a3da37af52ead686489cbf04bd)
3cc9e98506d is described below
commit 3cc9e98506d2777bb032839dd356ab6011819674
Author: tvm-bot <[email protected]>
AuthorDate: Mon Feb 23 20:20:34 2026 +0000
deploying docs (apache/tvm@d4633957069120a3da37af52ead686489cbf04bd)
---
.../11c11e53c7dace51a8be968ee169ed0d/ir_module.zip | Bin 23874 -> 23874 bytes
.../tir_transformation.zip | Bin 15631 -> 15631 bytes
.../relax_creation.zip | Bin 22418 -> 22418 bytes
.../relax_transformation.zip | Bin 11480 -> 11480 bytes
.../optimize_llm.zip | Bin 54183 -> 54183 bytes
.../e2e_opt_model.zip | Bin 14509 -> 14509 bytes
.../quick_start.zip | Bin 16252 -> 16252 bytes
.../export_and_load_executable.zip | Bin 31492 -> 31492 bytes
.../tir_creation.zip | Bin 24417 -> 24417 bytes
.../cross_compilation_and_rpc.zip | Bin 47233 -> 47233 bytes
.../customize_opt.zip | Bin 20568 -> 20568 bytes
.../relax/tutorials/sg_execution_times.rst.txt | 2 +-
.../tensor_ir/tutorials/sg_execution_times.rst.txt | 6 +++---
.../tensor_ir/tutorials/tir_creation.rst.txt | 20 ++++++++---------
.../tensor_ir/tutorials/tir_transformation.rst.txt | 6 +++---
.../get_started/tutorials/ir_module.rst.txt | 8 +++----
.../get_started/tutorials/quick_start.rst.txt | 4 ++--
.../tutorials/sg_execution_times.rst.txt | 6 +++---
.../tutorials/cross_compilation_and_rpc.rst.txt | 6 +++---
.../how_to/tutorials/customize_opt.rst.txt | 4 ++--
.../how_to/tutorials/e2e_opt_model.rst.txt | 2 +-
.../how_to/tutorials/sg_execution_times.rst.txt | 10 ++++-----
docs/_sources/sg_execution_times.rst.txt | 18 ++++++++--------
.../relax/tutorials/sg_execution_times.html | 2 +-
.../tensor_ir/tutorials/sg_execution_times.html | 6 +++---
.../tensor_ir/tutorials/tir_creation.html | 20 ++++++++---------
.../tensor_ir/tutorials/tir_transformation.html | 6 +++---
docs/get_started/tutorials/ir_module.html | 16 +++++++-------
docs/get_started/tutorials/quick_start.html | 24 ++++++++++-----------
docs/get_started/tutorials/sg_execution_times.html | 6 +++---
.../tutorials/cross_compilation_and_rpc.html | 6 +++---
docs/how_to/tutorials/customize_opt.html | 8 +++----
docs/how_to/tutorials/e2e_opt_model.html | 6 +++---
.../tutorials/export_and_load_executable.html | 8 +++----
docs/how_to/tutorials/optimize_llm.html | 10 ++++-----
docs/how_to/tutorials/sg_execution_times.html | 10 ++++-----
docs/objects.inv | Bin 18841 -> 18848 bytes
docs/reference/api/python/relax/relax.html | 2 +-
docs/reference/api/python/runtime/vm.html | 2 +-
docs/searchindex.js | 2 +-
docs/sg_execution_times.html | 18 ++++++++--------
41 files changed, 122 insertions(+), 122 deletions(-)
diff --git a/docs/_downloads/11c11e53c7dace51a8be968ee169ed0d/ir_module.zip
b/docs/_downloads/11c11e53c7dace51a8be968ee169ed0d/ir_module.zip
index 7d2956b2c99..5e0d3e2469b 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 144a4f88c62..fe0ab881807 100644
Binary files
a/docs/_downloads/18ba0d2ee8120824175aaef66bc9c9bf/tir_transformation.zip and
b/docs/_downloads/18ba0d2ee8120824175aaef66bc9c9bf/tir_transformation.zip differ
diff --git
a/docs/_downloads/4753776bbe68e7c9ee4d19117973fc8b/relax_creation.zip
b/docs/_downloads/4753776bbe68e7c9ee4d19117973fc8b/relax_creation.zip
index c60c17fafe4..a300c559e05 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 178769fcd82..701b70a2a14 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 2f16392b967..9a8faa0f7ad 100644
Binary files
a/docs/_downloads/83e85f38cf16f1d926d06615fd54095c/optimize_llm.zip and
b/docs/_downloads/83e85f38cf16f1d926d06615fd54095c/optimize_llm.zip differ
diff --git a/docs/_downloads/a7dd7652b2ad50f82d7b739ce3645799/e2e_opt_model.zip
b/docs/_downloads/a7dd7652b2ad50f82d7b739ce3645799/e2e_opt_model.zip
index 09a73a4b3c4..4cad0da7c97 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 e37cde5b111..4ab09060d07 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 f90665abf79..027ad9dc243 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 44b0a2e01db..79ba6d2f405 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 ca44616dc42..c42938a8948 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 f6d71fcd5a9..6ebfa55e03d 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.txt
b/docs/_sources/deep_dive/relax/tutorials/sg_execution_times.rst.txt
index f28d27384b8..831cf48d530 100644
--- a/docs/_sources/deep_dive/relax/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/deep_dive/relax/tutorials/sg_execution_times.rst.txt
@@ -6,7 +6,7 @@
Computation times
=================
-**00:00.175** total execution time for 2 files **from
deep_dive/relax/tutorials**:
+**00:00.176** total execution time for 2 files **from
deep_dive/relax/tutorials**:
.. container::
diff --git
a/docs/_sources/deep_dive/tensor_ir/tutorials/sg_execution_times.rst.txt
b/docs/_sources/deep_dive/tensor_ir/tutorials/sg_execution_times.rst.txt
index 78cd1871af4..b2f54ea58c8 100644
--- a/docs/_sources/deep_dive/tensor_ir/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/deep_dive/tensor_ir/tutorials/sg_execution_times.rst.txt
@@ -6,7 +6,7 @@
Computation times
=================
-**00:00.462** total execution time for 2 files **from
deep_dive/tensor_ir/tutorials**:
+**00:00.467** total execution time for 2 files **from
deep_dive/tensor_ir/tutorials**:
.. container::
@@ -33,8 +33,8 @@ Computation times
- Time
- Mem (MB)
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_tir_transformation.py`
(``tir_transformation.py``)
- - 00:00.292
+ - 00:00.295
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_tir_creation.py`
(``tir_creation.py``)
- - 00:00.170
+ - 00:00.173
- 0.0
diff --git a/docs/_sources/deep_dive/tensor_ir/tutorials/tir_creation.rst.txt
b/docs/_sources/deep_dive/tensor_ir/tutorials/tir_creation.rst.txt
index 82f196d81cd..4f7852b4b73 100644
--- a/docs/_sources/deep_dive/tensor_ir/tutorials/tir_creation.rst.txt
+++ b/docs/_sources/deep_dive/tensor_ir/tutorials/tir_creation.rst.txt
@@ -319,17 +319,17 @@ Now let's check the runtime dynamic shape inference:
.. code-block:: none
- [[1.0687387 1.7051318 0.53478473 1.2447947 ]
- [0.7868451 1.0988005 0.5212298 0.7379694 ]
- [0.59672266 1.1634411 0.8761779 1.6228483 ]
- [0.96112955 1.6041667 1.0700647 1.8662562 ]]
- [[31.131159 30.285185 32.26687 ... 33.98063 31.474232 32.56088 ]
- [31.128223 32.93424 30.910475 ... 34.165596 32.894897 32.72144 ]
- [31.077154 31.886332 32.360718 ... 35.320423 33.263638 34.036896]
+ [[1.1769985 1.2572315 1.1415789 1.0133203 ]
+ [1.2764876 1.0447661 0.66577244 0.78141856]
+ [1.0145769 1.106837 0.9101097 0.8087496 ]
+ [0.8890752 0.849807 0.7336039 0.65813607]]
+ [[30.404625 33.646057 33.519825 ... 33.448086 30.380777 30.60512 ]
+ [29.384144 32.906975 31.675583 ... 32.788273 27.780428 27.227789]
+ [31.738853 33.849815 33.60188 ... 34.209877 31.041008 28.577234]
...
- [30.598007 32.030666 31.956154 ... 34.328274 31.760609 34.897697]
- [29.185843 31.302677 29.177567 ... 33.337902 30.030025 34.534695]
- [29.86443 31.52192 29.263405 ... 32.486103 30.365438 32.073902]]
+ [32.214645 33.77155 35.148952 ... 33.381836 30.82872 31.09151 ]
+ [34.32221 34.37794 35.519894 ... 35.138638 32.85187 30.50213 ]
+ [29.590946 30.900402 30.792732 ... 33.40585 28.857025 26.465826]]
diff --git
a/docs/_sources/deep_dive/tensor_ir/tutorials/tir_transformation.rst.txt
b/docs/_sources/deep_dive/tensor_ir/tutorials/tir_transformation.rst.txt
index 8578b6e6c8e..123fdc10530 100644
--- a/docs/_sources/deep_dive/tensor_ir/tutorials/tir_transformation.rst.txt
+++ b/docs/_sources/deep_dive/tensor_ir/tutorials/tir_transformation.rst.txt
@@ -117,7 +117,7 @@ original implementation.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2.7287 2.7287 2.7287 2.7287 0.0000
+ 2.7383 2.7383 2.7383 2.7383 0.0000
@@ -289,7 +289,7 @@ action involves reordering these two loops.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 0.8568 0.8568 0.8568 0.8568 0.0000
+ 0.8579 0.8579 0.8579 0.8579 0.0000
@@ -417,7 +417,7 @@ from the reduction update via the **decompose_reduction**
primitive.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 0.3380 0.3380 0.3380 0.3380 0.0000
+ 0.3377 0.3377 0.3377 0.3377 0.0000
diff --git a/docs/_sources/get_started/tutorials/ir_module.rst.txt
b/docs/_sources/get_started/tutorials/ir_module.rst.txt
index 1ac9f9659ba..44b520297ab 100644
--- a/docs/_sources/get_started/tutorials/ir_module.rst.txt
+++ b/docs/_sources/get_started/tutorials/ir_module.rst.txt
@@ -694,8 +694,8 @@ We can deploy the IRModule on CPU by specifying the target
as ``llvm``.
.. code-block:: none
- [[-0.01371826 -0.04909292 -0.07197412 -0.06977656 0.11713963 0.02887076
- 0.08924652 -0.27186972 0.05595757 -0.11292398]]
+ [[ 0.03734957 -0.11577559 0.07155224 0.02716034 0.09010193 0.4489682
+ 0.07317595 0.18780974 0.05461347 -0.00979966]]
@@ -761,8 +761,8 @@ Now we can compile the IRModule on GPU, the similar way as
we did on CPU.
.. code-block:: none
- [[-0.01371826 -0.04909296 -0.07197418 -0.06977656 0.11713966 0.02887076
- 0.08924655 -0.27186978 0.05595753 -0.11292395]]
+ [[ 0.03734961 -0.11577554 0.07155231 0.02716034 0.09010193 0.44896832
+ 0.07317595 0.18780974 0.05461347 -0.00979968]]
diff --git a/docs/_sources/get_started/tutorials/quick_start.rst.txt
b/docs/_sources/get_started/tutorials/quick_start.rst.txt
index dab94c475f5..973a3141634 100644
--- a/docs/_sources/get_started/tutorials/quick_start.rst.txt
+++ b/docs/_sources/get_started/tutorials/quick_start.rst.txt
@@ -224,8 +224,8 @@ different devices.
.. code-block:: none
- [[24482.695 26273.605 26221.25 25371.219 25193.14 25728.459 26213.656
- 26440.39 25291.395 24768.943]]
+ [[25907.166 23492.523 25295.543 24138.213 25481.852 25200.75 25039.266
+ 24356.322 24633.045 22952.268]]
diff --git a/docs/_sources/get_started/tutorials/sg_execution_times.rst.txt
b/docs/_sources/get_started/tutorials/sg_execution_times.rst.txt
index a5f869d7bc8..f98016a5c37 100644
--- a/docs/_sources/get_started/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/get_started/tutorials/sg_execution_times.rst.txt
@@ -6,7 +6,7 @@
Computation times
=================
-**00:06.213** total execution time for 2 files **from get_started/tutorials**:
+**00:06.109** 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``)
- - 00:06.041
+ - 00:05.937
- 0.0
* - :ref:`sphx_glr_get_started_tutorials_quick_start.py`
(``quick_start.py``)
- - 00:00.172
+ - 00:00.173
- 0.0
diff --git a/docs/_sources/how_to/tutorials/cross_compilation_and_rpc.rst.txt
b/docs/_sources/how_to/tutorials/cross_compilation_and_rpc.rst.txt
index 0e199cccabc..3711454824d 100644
--- a/docs/_sources/how_to/tutorials/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/how_to/tutorials/cross_compilation_and_rpc.rst.txt
@@ -266,7 +266,7 @@ device and returns the measured cost. Network overhead is
excluded.
.. code-block:: none
- 1.17e-07 secs/op
+ 1.12e-07 secs/op
@@ -651,8 +651,8 @@ 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/tmpg7pb2i6l/model_deployed.so
- Saved parameters to: /tmp/tmpg7pb2i6l/model_params.npz
+ Exported library to: /tmp/tmpfee9hh49/model_deployed.so
+ Saved parameters to: /tmp/tmpfee9hh49/model_params.npz
RPC workflow (works for any remote device):
==================================================
diff --git a/docs/_sources/how_to/tutorials/customize_opt.rst.txt
b/docs/_sources/how_to/tutorials/customize_opt.rst.txt
index 2d3d5d644e6..17cf3685761 100644
--- a/docs/_sources/how_to/tutorials/customize_opt.rst.txt
+++ b/docs/_sources/how_to/tutorials/customize_opt.rst.txt
@@ -425,8 +425,8 @@ We can build and deploy the optimized model to the TVM
runtime.
.. code-block:: none
- [[25882.344 26176.549 25374.908 25411.805 23633.246 24337.842 24618.688
- 26268.145 25842.059 25533.342]]
+ [[24750.184 25984.256 24911.973 24691.074 25399.715 25066.629 24797.062
+ 23657.46 25855.477 24778.65 ]]
diff --git a/docs/_sources/how_to/tutorials/e2e_opt_model.rst.txt
b/docs/_sources/how_to/tutorials/e2e_opt_model.rst.txt
index 44f6b238797..9ba3c66f480 100644
--- a/docs/_sources/how_to/tutorials/e2e_opt_model.rst.txt
+++ b/docs/_sources/how_to/tutorials/e2e_opt_model.rst.txt
@@ -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] 33%|███▎ |
14.9M/44.7M [00:00<00:00, 156MB/s] 100%|██████████| 44.7M/44.7M
[00:00<00:00, 250MB/s]
+ 0%| | 0.00/44.7M [00:00<?, ?B/s] 58%|█████▊ |
26.1M/44.7M [00:00<00:00, 273MB/s] 100%|██████████| 44.7M/44.7M
[00:00<00:00, 289MB/s]
diff --git a/docs/_sources/how_to/tutorials/sg_execution_times.rst.txt
b/docs/_sources/how_to/tutorials/sg_execution_times.rst.txt
index 0b261405782..492c98e8fe0 100644
--- a/docs/_sources/how_to/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tutorials/sg_execution_times.rst.txt
@@ -6,7 +6,7 @@
Computation times
=================
-**00:34.061** total execution time for 5 files **from how_to/tutorials**:
+**00:34.449** total execution time for 5 files **from how_to/tutorials**:
.. container::
@@ -33,16 +33,16 @@ Computation times
- Time
- Mem (MB)
* - :ref:`sphx_glr_how_to_tutorials_optimize_llm.py` (``optimize_llm.py``)
- - 00:32.321
+ - 00:32.768
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_customize_opt.py` (``customize_opt.py``)
- - 00:00.670
+ - 00:00.653
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_cross_compilation_and_rpc.py`
(``cross_compilation_and_rpc.py``)
- - 00:00.573
+ - 00:00.580
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_e2e_opt_model.py` (``e2e_opt_model.py``)
- - 00:00.495
+ - 00:00.445
- 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.txt
b/docs/_sources/sg_execution_times.rst.txt
index db1c846ea37..49e32d7d007 100644
--- a/docs/_sources/sg_execution_times.rst.txt
+++ b/docs/_sources/sg_execution_times.rst.txt
@@ -6,7 +6,7 @@
Computation times
=================
-**00:40.911** total execution time for 11 files **from all galleries**:
+**00:41.202** total execution time for 11 files **from all galleries**:
.. container::
@@ -33,28 +33,28 @@ Computation times
- Time
- Mem (MB)
* - :ref:`sphx_glr_how_to_tutorials_optimize_llm.py`
(``../how_to/tutorials/optimize_llm.py``)
- - 00:32.321
+ - 00:32.768
- 0.0
* - :ref:`sphx_glr_get_started_tutorials_ir_module.py`
(``../get_started/tutorials/ir_module.py``)
- - 00:06.041
+ - 00:05.937
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_customize_opt.py`
(``../how_to/tutorials/customize_opt.py``)
- - 00:00.670
+ - 00:00.653
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_cross_compilation_and_rpc.py`
(``../how_to/tutorials/cross_compilation_and_rpc.py``)
- - 00:00.573
+ - 00:00.580
- 0.0
* - :ref:`sphx_glr_how_to_tutorials_e2e_opt_model.py`
(``../how_to/tutorials/e2e_opt_model.py``)
- - 00:00.495
+ - 00:00.445
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_tir_transformation.py`
(``../deep_dive/tensor_ir/tutorials/tir_transformation.py``)
- - 00:00.292
+ - 00:00.295
- 0.0
* - :ref:`sphx_glr_get_started_tutorials_quick_start.py`
(``../get_started/tutorials/quick_start.py``)
- - 00:00.172
+ - 00:00.173
- 0.0
* - :ref:`sphx_glr_deep_dive_tensor_ir_tutorials_tir_creation.py`
(``../deep_dive/tensor_ir/tutorials/tir_creation.py``)
- - 00:00.170
+ - 00:00.173
- 0.0
* - :ref:`sphx_glr_deep_dive_relax_tutorials_relax_creation.py`
(``../deep_dive/relax/tutorials/relax_creation.py``)
- 00:00.109
diff --git a/docs/deep_dive/relax/tutorials/sg_execution_times.html
b/docs/deep_dive/relax/tutorials/sg_execution_times.html
index 58fa03ea91c..5ed58b70cf5 100644
--- a/docs/deep_dive/relax/tutorials/sg_execution_times.html
+++ b/docs/deep_dive/relax/tutorials/sg_execution_times.html
@@ -294,7 +294,7 @@
<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>00:00.175</strong> total execution time for 2 files <strong>from
deep_dive/relax/tutorials</strong>:</p>
+<p><strong>00:00.176</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" />
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 3a29c2ecec5..eec72e8c8ef 100644
--- a/docs/deep_dive/tensor_ir/tutorials/sg_execution_times.html
+++ b/docs/deep_dive/tensor_ir/tutorials/sg_execution_times.html
@@ -294,7 +294,7 @@
<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>00:00.462</strong> total execution time for 2 files <strong>from
deep_dive/tensor_ir/tutorials</strong>:</p>
+<p><strong>00:00.467</strong> total execution time for 2 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" />
@@ -316,11 +316,11 @@ $(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>00:00.292</p></td>
+<td><p>00:00.295</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><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>00:00.170</p></td>
+<td><p>00:00.173</p></td>
<td><p>0.0</p></td>
</tr>
</tbody>
diff --git a/docs/deep_dive/tensor_ir/tutorials/tir_creation.html
b/docs/deep_dive/tensor_ir/tutorials/tir_creation.html
index 65cf819a7f6..df43b1efa8b 100644
--- a/docs/deep_dive/tensor_ir/tutorials/tir_creation.html
+++ b/docs/deep_dive/tensor_ir/tutorials/tir_creation.html
@@ -490,17 +490,17 @@ be used to ascertain the shape and data type of a
TensorIR.</p>
<span class="nb">print</span><span class="p">(</span><span
class="n">evaluate_dynamic_shape</span><span class="p">(</span><span
class="n">dyn_shape_lib</span><span class="p">,</span> <span
class="n">m</span><span class="o">=</span><span class="mi">64</span><span
class="p">,</span> <span class="n">n</span><span class="o">=</span><span
class="mi">64</span><span class="p">,</span> <a
href="../../../reference/api/python/tir/tir.html#tvm.tir.IterVar"
title="tvm.tir.IterVar" class="sphx-glr-ba [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[1.0687387 1.7051318 0.53478473
1.2447947 ]
- [0.7868451 1.0988005 0.5212298 0.7379694 ]
- [0.59672266 1.1634411 0.8761779 1.6228483 ]
- [0.96112955 1.6041667 1.0700647 1.8662562 ]]
-[[31.131159 30.285185 32.26687 ... 33.98063 31.474232 32.56088 ]
- [31.128223 32.93424 30.910475 ... 34.165596 32.894897 32.72144 ]
- [31.077154 31.886332 32.360718 ... 35.320423 33.263638 34.036896]
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[1.1769985 1.2572315 1.1415789
1.0133203 ]
+ [1.2764876 1.0447661 0.66577244 0.78141856]
+ [1.0145769 1.106837 0.9101097 0.8087496 ]
+ [0.8890752 0.849807 0.7336039 0.65813607]]
+[[30.404625 33.646057 33.519825 ... 33.448086 30.380777 30.60512 ]
+ [29.384144 32.906975 31.675583 ... 32.788273 27.780428 27.227789]
+ [31.738853 33.849815 33.60188 ... 34.209877 31.041008 28.577234]
...
- [30.598007 32.030666 31.956154 ... 34.328274 31.760609 34.897697]
- [29.185843 31.302677 29.177567 ... 33.337902 30.030025 34.534695]
- [29.86443 31.52192 29.263405 ... 32.486103 30.365438 32.073902]]
+ [32.214645 33.77155 35.148952 ... 33.381836 30.82872 31.09151 ]
+ [34.32221 34.37794 35.519894 ... 35.138638 32.85187 30.50213 ]
+ [29.590946 30.900402 30.792732 ... 33.40585 28.857025 26.465826]]
</pre></div>
</div>
</section>
diff --git a/docs/deep_dive/tensor_ir/tutorials/tir_transformation.html
b/docs/deep_dive/tensor_ir/tutorials/tir_transformation.html
index 3f483932788..ccc16741810 100644
--- a/docs/deep_dive/tensor_ir/tutorials/tir_transformation.html
+++ b/docs/deep_dive/tensor_ir/tutorials/tir_transformation.html
@@ -368,7 +368,7 @@ 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)
- 2.7287 2.7287 2.7287 2.7287 0.0000
+ 2.7383 2.7383 2.7383 2.7383 0.0000
</pre></div>
</div>
<section id="initialization-schedule">
@@ -464,7 +464,7 @@ class Module:
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 0.8568 0.8568 0.8568 0.8568 0.0000
+ 0.8579 0.8579 0.8579 0.8579 0.0000
</pre></div>
</div>
</section>
@@ -558,7 +558,7 @@ class Module:
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 0.3380 0.3380 0.3380 0.3380 0.0000
+ 0.3377 0.3377 0.3377 0.3377 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 0fd68ce1065..df9e69750e9 100644
--- a/docs/get_started/tutorials/ir_module.html
+++ b/docs/get_started/tutorials/ir_module.html
@@ -806,16 +806,16 @@ backends.</p>
<p>We can deploy the IRModule on CPU by specifying the target as <code
class="docutils literal notranslate"><span class="pre">llvm</span></code>.</p>
<div class="highlight-Python notranslate"><div
class="highlight"><pre><span></span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">exec</span></a> <span class="o">=</span> <a
href="../../reference/api/python/driver.html#tvm.compile" title="tvm.compile"
class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-func [...]
<span class="n">dev</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">cpu</span><span
class="p">()</span>
-<a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a> <span
class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span class=" [...]
+<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class [...]
<span class="n">raw_data</span> <span class="o">=</span> <span
class="n">np</span><span class="o">.</span><span class="n">random</span><span
class="o">.</span><span class="n">rand</span><span class="p">(</span><span
class="mi">1</span><span class="p">,</span> <span class="mi">784</span><span
class="p">)</span><span class="o">.</span><span class="n">astype</span><span
class="p">(</span><span class="s2">"float32"</span><span
class="p">)</span>
<span class="n">data</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">runtime</span><span
class="o">.</span><span class="n">tensor</span><span class="p">(</span><span
class="n">raw_data</span><span class="p">,</span> <span
class="n">dev</span><span class="p">)</span>
-<span class="n">cpu_out</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">[</span><span class="s2">"main"</span><span
class="p">](</span><span class="n">data</span><span class="p">,</span> <span
class="o">*</span><a href="https:// [...]
+<span class="n">cpu_out</span> <span class="o">=</span> <span
class="n">vm</span><span class="p">[</span><span
class="s2">"main"</span><span class="p">](</span><span
class="n">data</span><span class="p">,</span> <span class="o">*</span><a
href="https://docs.python.org/3/library/stdtypes.html#dict";
title="builtins.dict" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">params_from_torch</span></a><span class="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>[[-0.01371826 -0.04909292 -0.07197412
-0.06977656 0.11713963 0.02887076
- 0.08924652 -0.27186972 0.05595757 -0.11292398]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[ 0.03734957 -0.11577559 0.07155224
0.02716034 0.09010193 0.4489682
+ 0.07317595 0.18780974 0.05461347 -0.00979966]]
</pre></div>
</div>
</section>
@@ -838,19 +838,19 @@ the details of <code class="docutils literal
notranslate"><span class="pre">DLig
<p>Now we can compile the IRModule on GPU, the similar way as we did on
CPU.</p>
<div class="highlight-Python notranslate"><div
class="highlight"><pre><span></span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">exec</span></a> <span class="o">=</span> <a
href="../../reference/api/python/driver.html#tvm.compile" title="tvm.compile"
class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-func [...]
<span class="n">dev</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">device</span><span
class="p">(</span><span class="s2">"cuda"</span><span
class="p">,</span> <span class="mi">0</span><span class="p">)</span>
-<a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a> <span
class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span class=" [...]
+<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class [...]
<span class="c1"># Need to allocate data and params on GPU device</span>
<span class="n">data</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">runtime</span><span
class="o">.</span><span class="n">tensor</span><span class="p">(</span><span
class="n">raw_data</span><span class="p">,</span> <span
class="n">dev</span><span class="p">)</span>
<a href="https://docs.python.org/3/library/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">gpu_params</span></a> <span class="o">=</span> <span
class="p">[</span><span class="n">tvm</span><span class="o">.</span><span
class="n">runtime</span><span class="o">.</span><span
class="n">tensor</span><span class="p">(</span><span class="n">p</span><span
class="p">,</span> <span class="n"> [...]
-<span class="n">gpu_out</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">[</span><span class="s2">"main"</span><span
class="p">](</span><span class="n">data</span><span class="p">,</span> <span
class="o">*</span><a href="https:// [...]
+<span class="n">gpu_out</span> <span class="o">=</span> <span
class="n">vm</span><span class="p">[</span><span
class="s2">"main"</span><span class="p">](</span><span
class="n">data</span><span class="p">,</span> <span class="o">*</span><a
href="https://docs.python.org/3/library/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">gpu_params</span></a><span class="p">)</span><s [...]
<span class="nb">print</span><span class="p">(</span><span
class="n">gpu_out</span><span class="p">)</span>
<span class="c1"># Check the correctness of the results</span>
<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>[[-0.01371826 -0.04909296 -0.07197418
-0.06977656 0.11713966 0.02887076
- 0.08924655 -0.27186978 0.05595753 -0.11292395]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[ 0.03734961 -0.11577554 0.07155231
0.02716034 0.09010193 0.44896832
+ 0.07317595 0.18780974 0.05461347 -0.00979968]]
</pre></div>
</div>
</section>
diff --git a/docs/get_started/tutorials/quick_start.html
b/docs/get_started/tutorials/quick_start.html
index 84d972bc3f2..289a0e33173 100644
--- a/docs/get_started/tutorials/quick_start.html
+++ b/docs/get_started/tutorials/quick_start.html
@@ -449,16 +449,16 @@ different devices.</p>
<a href="../../reference/api/python/target.html#tvm.target.Target"
title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">target</span></a> <span class="o">=</span> <a
href="../../reference/api/python/target.html#tvm.target.Target"
title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target
sphx-glr-backref-type-py-class"><span class="n">tvm</span><span
class="o">.</span><span class="n">target< [...]
<a href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">ex</span></a> <span class="o">=</span> <a
href="../../reference/api/python/driver.html#tvm.compile" title="tvm.compile"
class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span
class="n">tvm</span><span class="o">.</span><span class="n">compile</span [...]
<span class="n">device</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">cpu</span><span
class="p">()</span>
-<a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a> <span
class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span class=" [...]
+<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class [...]
<span class="n">data</span> <span class="o">=</span> <span
class="n">np</span><span class="o">.</span><span class="n">random</span><span
class="o">.</span><span class="n">rand</span><span class="p">(</span><span
class="mi">1</span><span class="p">,</span> <span class="mi">784</span><span
class="p">)</span><span class="o">.</span><span class="n">astype</span><span
class="p">(</span><span class="s2">"float32"</span><span
class="p">)</span>
<span class="n">tvm_data</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">runtime</span><span
class="o">.</span><span class="n">tensor</span><span class="p">(</span><span
class="n">data</span><span class="p">,</span> <span
class="n">device</span><span class="o">=</span><span
class="n">device</span><span class="p">)</span>
<a href="https://docs.python.org/3/library/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="o">=</span> <span
class="p">[</span><span class="n">np</span><span class="o">.</span><span
class="n">random</span><span class="o">.</span><span class="n">rand</span><span
class="p">(</span><span class="o">*</span><span class="n">param</span><span
class="o">.</sp [...]
<a href="https://docs.python.org/3/library/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="o">=</span> <span
class="p">[</span><span class="n">tvm</span><span class="o">.</span><span
class="n">runtime</span><span class="o">.</span><span
class="n">tensor</span><span class="p">(</span><span
class="n">param</span><span class="p">,</span> <span class="n"> [...]
-<span class="nb">print</span><span class="p">(</span><a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><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="http [...]
+<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/library/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><s [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[24482.695 26273.605 26221.25 25371.219
25193.14 25728.459 26213.656
- 26440.39 25291.395 24768.943]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[25907.166 23492.523 25295.543 24138.213
25481.852 25200.75 25039.266
+ 24356.322 24633.045 22952.268]]
</pre></div>
</div>
<p>Our goal is to bring machine learning to the application with any language
of interest,
@@ -466,8 +466,8 @@ with the minimum runtime support.</p>
<ul>
<li><p>Each function in IRModule becomes a runnable function in the runtime.
For example in LLM
cases, we can call <code class="docutils literal notranslate"><span
class="pre">prefill</span></code> and <code class="docutils literal
notranslate"><span class="pre">decode</span></code> functions directly.</p>
-<div class="highlight-Python notranslate"><div
class="highlight"><pre><span></span><span class="n">prefill_logits</span> <span
class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">[</span><span class="s2">"prefill"</span><span
class="p">](</span> [...]
-<span class="n">decoded_logits</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">[</span><span class="s2">"decode"</span><span
class="p">](</span><span class="n">inputs</span><span class="p">,</span> <span
class="n">weight</span>< [...]
+<div class="highlight-Python notranslate"><div
class="highlight"><pre><span></span><span class="n">prefill_logits</span> <span
class="o">=</span> <span class="n">vm</span><span class="p">[</span><span
class="s2">"prefill"</span><span class="p">](</span><span
class="n">inputs</span><span class="p">,</span> <span
class="n">weight</span><span class="p">,</span> <span
class="n">kv_cache</span><span class="p">)</span>
+<span class="n">decoded_logits</span> <span class="o">=</span> <span
class="n">vm</span><span class="p">[</span><span
class="s2">"decode"</span><span class="p">](</span><span
class="n">inputs</span><span class="p">,</span> <span
class="n">weight</span><span class="p">,</span> <span
class="n">kv_cache</span><span class="p">)</span>
</pre></div>
</div>
</li>
@@ -482,15 +482,15 @@ copy exchange with existing ecosystem (DLPack exchange
with PyTorch)</p>
</li>
<li><p>TVM runtime works in non-python environments, so it works on settings
such as mobile</p>
<div class="highlight-C++ notranslate"><div
class="highlight"><pre><span></span><span class="c1">// C++ snippet</span>
-<span class="n">runtime</span><span class="o">::</span><span
class="n">Module</span><span class="w"> </span><a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span class="w">
</span><span class="o">=</span><span class="w"> </span><a
href="../../reference/api/python/relax/relax.html#tvm.r [...]
-<a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">.</span><span class="n">GetFunction</span><span
class="p">(</span><span class="s">"init"</span><span
class="p">)(...);</span>
-<span class="n">Tensor</span><span class="w"> </span><span
class="n">out</span><span class="w"> </span><span class="o">=</span><span
class="w"> </span><a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">.</span><span class="n">GetFunction</span><span
class="p">(</span><span [...]
+<span class="n">runtime</span><span class="o">::</span><span
class="n">Module</span><span class="w"> </span><span class="n">vm</span><span
class="w"> </span><span class="o">=</span><span class="w"> </span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">ex</span></a><span class="p">.</span><span class="n">GetFunction [...]
+<span class="n">vm</span><span class="p">.</span><span
class="n">GetFunction</span><span class="p">(</span><span
class="s">"init"</span><span class="p">)(...);</span>
+<span class="n">Tensor</span><span class="w"> </span><span
class="n">out</span><span class="w"> </span><span class="o">=</span><span
class="w"> </span><span class="n">vm</span><span class="p">.</span><span
class="n">GetFunction</span><span class="p">(</span><span
class="s">"prefill"</span><span class="p">)(</span><span
class="n">data</span><span class="p">,</span><span class="w"> </span><span
class="n">weight</span><span class="p">,</span><span class="w"> </span><span
class="n" [...]
</pre></div>
</div>
<div class="highlight-Java notranslate"><div
class="highlight"><pre><span></span><span class="c1">// Java snippet</span>
-<span class="n">Module</span><span class="w"> </span><a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span class="w">
</span><span class="o">=</span><span class="w"> </span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class [...]
-<a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">.</span><span class="na">getFunction</span><span
class="p">(</span><span class="s">"init"</span><span
class="p">).</span><span class="na">pushArg</span><span
class="p">(...).</span><span class="na">invoke</span>< [...]
-<span class="n">Tensor</span><span class="w"> </span><span
class="n">out</span><span class="w"> </span><span class="o">=</span><span
class="w"> </span><a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">.</span><span class="na">getFunction</span><span
class="p">(</span><spa [...]
+<span class="n">Module</span><span class="w"> </span><span
class="n">vm</span><span class="w"> </span><span class="o">=</span><span
class="w"> </span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">ex</span></a><span class="p">.</span><span
class="na">getFunction</span><span class="p">(</span><span class="s">"l
[...]
+<span class="n">vm</span><span class="p">.</span><span
class="na">getFunction</span><span class="p">(</span><span
class="s">"init"</span><span class="p">).</span><span
class="na">pushArg</span><span class="p">(...).</span><span
class="na">invoke</span><span class="p">;</span>
+<span class="n">Tensor</span><span class="w"> </span><span
class="n">out</span><span class="w"> </span><span class="o">=</span><span
class="w"> </span><span class="n">vm</span><span class="p">.</span><span
class="na">getFunction</span><span class="p">(</span><span
class="s">"prefill"</span><span class="p">).</span><span
class="na">pushArg</span><span class="p">(</span><span
class="n">data</span><span class="p">).</span><span
class="na">pushArg</span><span class="p">(</span><spa [...]
</pre></div>
</div>
</li>
diff --git a/docs/get_started/tutorials/sg_execution_times.html
b/docs/get_started/tutorials/sg_execution_times.html
index 10128d66770..dbe6f4a53b2 100644
--- a/docs/get_started/tutorials/sg_execution_times.html
+++ b/docs/get_started/tutorials/sg_execution_times.html
@@ -294,7 +294,7 @@
<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>00:06.213</strong> total execution time for 2 files <strong>from
get_started/tutorials</strong>:</p>
+<p><strong>00:06.109</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" />
@@ -316,11 +316,11 @@ $(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>00:06.041</p></td>
+<td><p>00:05.937</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>00:00.172</p></td>
+<td><p>00:00.173</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 2b456edf517..52e05a1d930 100644
--- a/docs/how_to/tutorials/cross_compilation_and_rpc.html
+++ b/docs/how_to/tutorials/cross_compilation_and_rpc.html
@@ -472,7 +472,7 @@ 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>1.17e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>1.12e-07 secs/op
</pre></div>
</div>
</section>
@@ -823,8 +823,8 @@ 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/tmpg7pb2i6l/model_deployed.so
-Saved parameters to: /tmp/tmpg7pb2i6l/model_params.npz
+Exported library to: /tmp/tmpfee9hh49/model_deployed.so
+Saved parameters to: /tmp/tmpfee9hh49/model_params.npz
RPC workflow (works for any remote device):
==================================================
diff --git a/docs/how_to/tutorials/customize_opt.html
b/docs/how_to/tutorials/customize_opt.html
index 6fdfaede422..17c57145e0f 100644
--- a/docs/how_to/tutorials/customize_opt.html
+++ b/docs/how_to/tutorials/customize_opt.html
@@ -609,16 +609,16 @@ pushing the performance to the limit. The current
optimization may not be the be
<p>We can build and deploy the optimized model to the TVM runtime.</p>
<div class="highlight-Python notranslate"><div
class="highlight"><pre><span></span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">ex</span></a> <span class="o">=</span> <a
href="../../reference/api/python/driver.html#tvm.compile" title="tvm.compile"
class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-functi [...]
<span class="n">dev</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">device</span><span
class="p">(</span><span class="s2">"cuda"</span><span
class="p">,</span> <span class="mi">0</span><span class="p">)</span>
-<a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a> <span
class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span class=" [...]
+<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class [...]
<span class="c1"># Need to allocate data and params on GPU device</span>
<span class="n">data</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">runtime</span><span
class="o">.</span><span class="n">tensor</span><span class="p">(</span><span
class="n">np</span><span class="o">.</span><span class="n">random</span><span
class="o">.</span><span class="n">rand</span><span class="p">(</span><span
class="o">*</span><a
href="https://docs.python.org/3/library/stdtypes.html#tuple";
title="builtins.tuple" class="sphx-glr-ba [...]
<a href="https://docs.python.org/3/library/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">gpu_params</span></a> <span class="o">=</span> <span
class="p">[</span><span class="n">tvm</span><span class="o">.</span><span
class="n">runtime</span><span class="o">.</span><span
class="n">tensor</span><span class="p">(</span><span class="n">np</span><span
class="o">.</span><span class="n"> [...]
-<span class="n">gpu_out</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">[</span><span class="s2">"forward"</span><span
class="p">](</span><span class="n">data</span><span class="p">,</span> <span
class="o">*</span><a href="https [...]
+<span class="n">gpu_out</span> <span class="o">=</span> <span
class="n">vm</span><span class="p">[</span><span
class="s2">"forward"</span><span class="p">](</span><span
class="n">data</span><span class="p">,</span> <span class="o">*</span><a
href="https://docs.python.org/3/library/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">gpu_params</span></a><span class="p">)</span [...]
<span class="nb">print</span><span class="p">(</span><span
class="n">gpu_out</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[25882.344 26176.549 25374.908 25411.805
23633.246 24337.842 24618.688
- 26268.145 25842.059 25533.342]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div
class="highlight"><pre><span></span>[[24750.184 25984.256 24911.973 24691.074
25399.715 25066.629 24797.062
+ 23657.46 25855.477 24778.65 ]]
</pre></div>
</div>
</section>
diff --git a/docs/how_to/tutorials/e2e_opt_model.html
b/docs/how_to/tutorials/e2e_opt_model.html
index 02092bf67ac..b4072ba6e69 100644
--- a/docs/how_to/tutorials/e2e_opt_model.html
+++ b/docs/how_to/tutorials/e2e_opt_model.html
@@ -329,8 +329,8 @@ 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]
- 33%|███▎ | 14.9M/44.7M [00:00<00:00, 156MB/s]
-100%|██████████| 44.7M/44.7M [00:00<00:00, 250MB/s]
+ 58%|█████▊ | 26.1M/44.7M [00:00<00:00, 273MB/s]
+100%|██████████| 44.7M/44.7M [00:00<00:00, 289MB/s]
</pre></div>
</div>
</section>
@@ -431,7 +431,7 @@ We skip this step in the CI environment.</p>
<span class="n">mod</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">tir</span><span
class="o">.</span><span class="n">transform</span><span class="o">.</span><span
class="n">DefaultGPUSchedule</span><span class="p">()(</span><span
class="n">mod</span><span class="p">)</span>
<span class="n">ex</span> <span class="o">=</span> <a
href="../../reference/api/python/driver.html#tvm.compile" title="tvm.compile"
class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span
class="n">tvm</span><span class="o">.</span><span
class="n">compile</span></a><span class="p">(</span><span
class="n">mod</span><span class="p">,</span> <a
href="../../reference/api/python/target.html#tvm.target.Target"
title="tvm.target.Target" class="sphx-glr-backref-module-tvm [...]
<span class="n">dev</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">device</span><span
class="p">(</span><span class="s2">"cuda"</span><span
class="p">,</span> <span class="mi">0</span><span class="p">)</span>
- <span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span class="n">relax</span><span
class="o">.</span><span class="n">VirtualMachine</span></a><span
class="p">(</span><span class="n">ex</span><span class="p">,</span> <span
class="n">dev</span><span class="p">)</span>
+ <span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><span
class="n">ex</span><span class="p">,</span> <span class="n">dev</span><span
class="p">)</span>
<span class="c1"># Need to allocate data and params on GPU device</span>
<span class="n">gpu_data</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">runtime</span><span
class="o">.</span><span class="n">tensor</span><span class="p">(</span><span
class="n">np</span><span class="o">.</span><span class="n">random</span><span
class="o">.</span><span class="n">rand</span><span class="p">(</span><span
class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span
class="p">,</span> <span class="mi">224< [...]
<span class="n">gpu_params</span> <span class="o">=</span> <span
class="p">[</span><span class="n">tvm</span><span class="o">.</span><span
class="n">runtime</span><span class="o">.</span><span
class="n">tensor</span><span class="p">(</span><span class="n">p</span><span
class="p">,</span> <span class="n">dev</span><span class="p">)</span> <span
class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span
class="n">params</span><span class="p">[</span><span class="s2" [...]
diff --git a/docs/how_to/tutorials/export_and_load_executable.html
b/docs/how_to/tutorials/export_and_load_executable.html
index 04274e32f0b..4731455cd73 100644
--- a/docs/how_to/tutorials/export_and_load_executable.html
+++ b/docs/how_to/tutorials/export_and_load_executable.html
@@ -441,7 +441,7 @@ runtime module directly.</p>
<div class="highlight-Python notranslate"><div
class="highlight"><pre><span></span><span class="k">if</span> <a
href="https://docs.python.org/3/library/functions.html#bool";
title="builtins.bool" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">RUN_EXAMPLE</span></a><span class="p">:</span>
<span class="n">loaded_rt_mod</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">runtime</span><span
class="o">.</span><span class="n">load_module</span><span
class="p">(</span><span class="nb">str</span><span class="p">(</span><span
class="n">library_path</span><span class="p">))</span>
<span class="n">dev</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">cpu</span><span
class="p">(</span><span class="mi">0</span><span class="p">)</span>
- <span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span class="n">relax</span><span
class="o">.</span><span class="n">VirtualMachine</span></a><span
class="p">(</span><span class="n">loaded_rt_mod</span><span class="p">,</span>
<span class="n">dev</span><span class="p">)</span>
+ <span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><span
class="n">loaded_rt_mod</span><span class="p">,</span> <span
class="n">dev</span><span class="p">)</span>
<span class="c1"># Prepare input data</span>
<span class="n">input_tensor</span> <span class="o">=</span> <span
class="n">torch</span><span class="o">.</span><span class="n">randn</span><span
class="p">(</span><span class="mi">1</span><span class="p">,</span> <span
class="mi">1</span><span class="p">,</span> <span class="mi">28</span><span
class="p">,</span> <span class="mi">28</span><span class="p">,</span> <span
class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span
class="o">.</span><span class="n">f [...]
@@ -522,7 +522,7 @@ of how to reload and run the model. Save this as <code
class="docutils literal n
<span class="c1"># Step 2: Create Virtual Machine</span>
<span class="n">device</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">cpu</span><span
class="p">(</span><span class="mi">0</span><span class="p">)</span>
-<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span class="n">relax</span><span
class="o">.</span><span class="n">VirtualMachine</span></a><span
class="p">(</span><span class="n">lib</span><span class="p">,</span> <span
class="n">device</span><span class="p">)</span>
+<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><span
class="n">lib</span><span class="p">,</span> <span class="n">device</span><span
class="p">)</span>
<span class="c1"># Step 3: Load parameters from the .npz file</span>
<span class="n">params_npz</span> <span class="o">=</span> <span
class="n">np</span><span class="o">.</span><span class="n">load</span><span
class="p">(</span><span
class="s2">"relax_export_artifacts/model_params.npz"</span><span
class="p">)</span>
@@ -557,7 +557,7 @@ To run on GPU instead of CPU, make the following
changes:</p>
</li>
<li><p><strong>Use GPU device in the script</strong>:</p>
<div class="highlight-python notranslate"><div
class="highlight"><pre><span></span><span class="n">device</span> <span
class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span
class="n">cuda</span><span class="p">(</span><span class="mi">0</span><span
class="p">)</span> <span class="c1"># Use CUDA device instead of CPU</span>
-<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span class="n">relax</span><span
class="o">.</span><span class="n">VirtualMachine</span></a><span
class="p">(</span><span class="n">lib</span><span class="p">,</span> <span
class="n">device</span><span class="p">)</span>
+<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><span
class="n">lib</span><span class="p">,</span> <span class="n">device</span><span
class="p">)</span>
<span class="c1"># Load parameters to GPU</span>
<span class="n">params</span> <span class="o">=</span> <span
class="p">[</span><span class="n">tvm</span><span class="o">.</span><span
class="n">runtime</span><span class="o">.</span><span
class="n">tensor</span><span class="p">(</span><span
class="n">params_npz</span><span class="p">[</span><span
class="sa">f</span><span class="s2">"p_</span><span
class="si">{</span><span class="n">i</span><span class="si">}</span><span
class="s2">"</span><span class="p">],</span> <span class= [...]
@@ -622,7 +622,7 @@ for a comprehensive guide on:</p>
<span class="c1"># Step 4: Load and run on remote device</span>
<span class="n">lib</span> <span class="o">=</span> <span
class="n">remote</span><span class="o">.</span><span
class="n">load_module</span><span class="p">(</span><span
class="s2">"mlp_arm.so"</span><span class="p">)</span>
-<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span class="n">relax</span><span
class="o">.</span><span class="n">VirtualMachine</span></a><span
class="p">(</span><span class="n">lib</span><span class="p">,</span> <span
class="n">remote</span><span class="o">.</span><span class="n">cpu</ [...]
+<span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><span
class="n">lib</span><span class="p">,</span> <span class="n">remote</span><span
class="o">.</span><span cla [...]
<span class="c1"># ... prepare input and params, then run inference</span>
</pre></div>
</div>
diff --git a/docs/how_to/tutorials/optimize_llm.html
b/docs/how_to/tutorials/optimize_llm.html
index 502f457cd50..10b137374a3 100644
--- a/docs/how_to/tutorials/optimize_llm.html
+++ b/docs/how_to/tutorials/optimize_llm.html
@@ -726,7 +726,7 @@ is designed specifically for the LLMs.</p>
<span class="k">with</span> <a
href="../../reference/api/python/target.html#tvm.target.Target"
title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">target</span></a><span class="p">:</span>
<a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">ex</span></a> <span class="o">=</span> <a
href="../../reference/api/python/driver.html#tvm.compile" title="tvm.compile"
class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span
class="n">tvm</span><span class="o">.</span><span class="n">compile</ [...]
- <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a> <span
class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm
sphx-glr-backref-type-py-class"><span cla [...]
+ <span class="n">vm</span> <span class="o">=</span> <a
href="../../reference/api/python/relax/relax.html#tvm.relax.VirtualMachine"
title="tvm.relax.VirtualMachine" class="sphx-glr-backref-module-tvm-relax
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">relax</span><span class="o">.</span><span
class="n">VirtualMachine</span></a><span class="p">(</span><a
href="../../reference/api/python/relax/relax.html#tvm.relax.VMExecutable"
title="tvm.relax.VMExecutable" c [...]
</pre></div>
</div>
</section>
@@ -824,7 +824,7 @@ the model documentation for the correct tokenization and
prompt format.</p>
key and value tensors for the attention layer. Apache TVM provides a
PagedKVCache to store the
key and value tensors. We create the PagedKVCache with the specified
parameters.</p>
<div class="highlight-Python notranslate"><div
class="highlight"><pre><span></span><span class="k">if</span> <span
class="ow">not</span> <a
href="https://docs.python.org/3/library/functions.html#bool";
title="builtins.bool" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span
class="n">IS_IN_CI</span></a><span class="p">:</span>
- <span class="n">kv_cache</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">[</span><span
class="s2">"create_tir_paged_kv_cache"</span><span class="p">](</span>
+ <span class="n">kv_cache</span> <span class="o">=</span> <span
class="n">vm</span><span class="p">[</span><span
class="s2">"create_tir_paged_kv_cache"</span><span class="p">](</span>
<a href="https://docs.python.org/3/library/stdtypes.html#tuple";
title="builtins.tuple" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class"><span class="n">ShapeTuple</span></a><span
class="p">([</span><span class="mi">1</span><span class="p">]),</span> <span
class="c1"># max_batch_size=1</span>
<a href="https://docs.python.org/3/library/stdtypes.html#tuple";
title="builtins.tuple" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class"><span class="n">ShapeTuple</span></a><span
class="p">([</span><span class="mi">2048</span><span class="p">]),</span>
<span class="c1"># max_total_seq_len=2048</span>
<a href="https://docs.python.org/3/library/stdtypes.html#tuple";
title="builtins.tuple" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class"><span class="n">ShapeTuple</span></a><span
class="p">([</span><span class="mi">2048</span><span class="p">]),</span>
<span class="c1"># prefill_chunk_size=2048</span>
@@ -841,7 +841,7 @@ compiled in the Relax IRModule to embed the tokens into the
hidden states.</p>
<span class="k">def</span><span class="w"> </span><span
class="nf">embed</span><span class="p">(</span><span
class="n">tokens</span><span class="p">,</span> <span
class="n">params</span><span class="p">):</span>
- <span class="n">_embed</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">[</span><span class="s2">"embed"</span><span
class="p">](</span><span class="n">tokens</span><span class="p">,</span> <span
class="n">params</span><span [...]
+ <span class="n">_embed</span> <span class="o">=</span> <span
class="n">vm</span><span class="p">[</span><span
class="s2">"embed"</span><span class="p">](</span><span
class="n">tokens</span><span class="p">,</span> <span
class="n">params</span><span class="p">)</span>
<span class="c1"># Reshape hidden from [seq_len, hidden_size] to [1,
seq_len, hidden_size]</span>
<span class="n">_embed</span> <span class="o">=</span> <span
class="n">nd_view_func</span><span class="p">(</span><span
class="n">_embed</span><span class="p">,</span> <a
href="https://docs.python.org/3/library/stdtypes.html#tuple";
title="builtins.tuple" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class"><span class="n">ShapeTuple</span></a><span
class="p">([</span><span class="mi">1</span><span class="p">,</span> <span
class="n">_embed</span><span class="o">.</s [...]
<span class="k">return</span> <span class="n">_embed</span>
@@ -864,7 +864,7 @@ and <cite>end_forward_func</cite> to end the forward
pass.</p>
<span class="n">add_sequence_func</span><span class="p">(</span><span
class="n">kv_cache</span><span class="p">,</span> <span
class="n">seq_id</span><span class="p">)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span
class="n">embed</span><span class="p">(</span><span
class="n">tokens</span><span class="p">,</span> <span
class="n">params</span><span class="p">)</span>
<span class="n">begin_forward_func</span><span class="p">(</span><span
class="n">kv_cache</span><span class="p">,</span> <a
href="https://docs.python.org/3/library/stdtypes.html#tuple";
title="builtins.tuple" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class"><span class="n">ShapeTuple</span></a><span
class="p">([</span><span class="n">seq_id</span><span class="p">]),</span> <a
href="https://docs.python.org/3/library/stdtypes.html#tuple";
title="builtins.tuple" cla [...]
- <span class="n">logits</span><span class="p">,</span> <span
class="n">kv_cache</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">[</span><span class="s2">"prefill"</span><span
class="p">](</span><span class="n">hidden_states</ [...]
+ <span class="n">logits</span><span class="p">,</span> <span
class="n">kv_cache</span> <span class="o">=</span> <span
class="n">vm</span><span class="p">[</span><span
class="s2">"prefill"</span><span class="p">](</span><span
class="n">hidden_states</span><span class="p">,</span> <span
class="n">kv_cache</span><span class="p">,</span> <span
class="n">params</span><span class="p">)</span>
<span class="n">end_forward_func</span><span class="p">(</span><span
class="n">kv_cache</span><span class="p">)</span>
</pre></div>
</div>
@@ -896,7 +896,7 @@ IRModule to generate the token.</p>
<span class="n">tokens</span> <span class="o">=</span> <span
class="n">tvm</span><span class="o">.</span><span class="n">runtime</span><span
class="o">.</span><span class="n">tensor</span><span class="p">(</span><span
class="n">np</span><span class="o">.</span><span class="n">array</span><span
class="p">([</span><span class="n">last_token</span><span
class="p">])</span><span class="o">.</span><span class="n">astype</span><span
class="p">(</span><span class="s2">"int32"< [...]
<span class="n">hidden_states</span> <span class="o">=</span> <span
class="n">embed</span><span class="p">(</span><span
class="n">tokens</span><span class="p">,</span> <span
class="n">params</span><span class="p">)</span>
<span class="n">begin_forward_func</span><span class="p">(</span><span
class="n">kv_cache</span><span class="p">,</span> <a
href="https://docs.python.org/3/library/stdtypes.html#tuple";
title="builtins.tuple" class="sphx-glr-backref-module-builtins
sphx-glr-backref-type-py-class"><span class="n">ShapeTuple</span></a><span
class="p">([</span><span class="n">seq_id</span><span class="p">]),</span> <a
href="https://docs.python.org/3/library/stdtypes.html#tuple";
title="builtins.tuple" [...]
- <span class="n">logits</span><span class="p">,</span> <span
class="n">kv_cache</span> <span class="o">=</span> <a
href="../../reference/api/python/runtime/vm.html#tvm.runtime.vm.VirtualMachine"
title="tvm.runtime.vm.VirtualMachine"
class="sphx-glr-backref-module-tvm-runtime-vm sphx-glr-backref-type-py-class
sphx-glr-backref-instance"><span class="n">vm</span></a><span
class="p">[</span><span class="s2">"decode"</span><span
class="p">](</span><span class="n">hidden_state [...]
+ <span class="n">logits</span><span class="p">,</span> <span
class="n">kv_cache</span> <span class="o">=</span> <span
class="n">vm</span><span class="p">[</span><span
class="s2">"decode"</span><span class="p">](</span><span
class="n">hidden_states</span><span class="p">,</span> <span
class="n">kv_cache</span><span class="p">,</span> <span
class="n">params</span><span class="p">)</span>
<span class="n">end_forward_func</span><span class="p">(</span><span
class="n">kv_cache</span><span class="p">)</span>
<span class="n">last_token</span> <span class="o">=</span> <span
class="n">sample_token</span><span class="p">(</span><span
class="n">logits</span><span class="p">)</span>
diff --git a/docs/how_to/tutorials/sg_execution_times.html
b/docs/how_to/tutorials/sg_execution_times.html
index c350bf0519e..d259df89146 100644
--- a/docs/how_to/tutorials/sg_execution_times.html
+++ b/docs/how_to/tutorials/sg_execution_times.html
@@ -294,7 +294,7 @@
<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>00:34.061</strong> total execution time for 5 files <strong>from
how_to/tutorials</strong>:</p>
+<p><strong>00:34.449</strong> total execution time for 5 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" />
@@ -316,19 +316,19 @@ $(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>00:32.321</p></td>
+<td><p>00:32.768</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><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>00:00.670</p></td>
+<td><p>00:00.653</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><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>00:00.573</p></td>
+<td><p>00:00.580</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><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>00:00.495</p></td>
+<td><p>00:00.445</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><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/objects.inv b/docs/objects.inv
index 353b65ebe02..190ef8fa33c 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/python/relax/relax.html
b/docs/reference/api/python/relax/relax.html
index 7169a4dd8d4..340175e62a6 100644
--- a/docs/reference/api/python/relax/relax.html
+++ b/docs/reference/api/python/relax/relax.html
@@ -2625,7 +2625,7 @@ 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.ir.IRModule"
title="tvm.ir.module.IRModule"><span
class="pre">IRModule</span></a></span></em>, < [...]
+<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.ir.IRModule"
title="tvm.ir.module.IRModule"><span
class="pre">IRModule</span></a></span></em>, < [...]
<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/reference/api/python/runtime/vm.html
b/docs/reference/api/python/runtime/vm.html
index 5ded5663406..28ba2d21ac3 100644
--- a/docs/reference/api/python/runtime/vm.html
+++ b/docs/reference/api/python/runtime/vm.html
@@ -490,7 +490,7 @@ more details.</p>
<div class="admonition seealso">
<p class="admonition-title">See also</p>
<dl class="simple">
-<dt><a class="reference internal"
href="#tvm.runtime.vm.VMInstrumentReturnKind"
title="tvm.runtime.vm.VMInstrumentReturnKind"><code class="xref py py-obj
docutils literal notranslate"><span
class="pre">VMInstrumentReturnKind</span></code></a></dt><dd><p>the possible
return values in VM.</p>
+<dt><a class="reference internal"
href="../relax/relax.html#tvm.relax.VMInstrumentReturnKind"
title="tvm.runtime.vm.VMInstrumentReturnKind"><code class="xref py py-obj
docutils literal notranslate"><span
class="pre">VMInstrumentReturnKind</span></code></a></dt><dd><p>the possible
return values in VM.</p>
</dd>
</dl>
</div>
diff --git a/docs/searchindex.js b/docs/searchindex.js
index bd569056872..602038aabcf 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Cross Compile TVM Runtime": [[40,
"cross-compile-tvm-runtime"]], "1. The lack of numpy on device machine caused
the RPC server can\u2019t be launched.": [[40,
"the-lack-of-numpy-on-device-machine-caused-the-rpc-server-can-t-be-launched"]],
"2. Pack and Deploy to Device Machine": [[40,
"pack-and-deploy-to-device-machine"]], "2. The lack of cloudpickle on device
machine caused the RPC server can\u2019t be launched.": [[40,
"the-lack-of-cloudpickle-on-devi [...]
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Cross Compile TVM Runtime": [[40,
"cross-compile-tvm-runtime"]], "1. The lack of numpy on device machine caused
the RPC server can\u2019t be launched.": [[40,
"the-lack-of-numpy-on-device-machine-caused-the-rpc-server-can-t-be-launched"]],
"2. Pack and Deploy to Device Machine": [[40,
"pack-and-deploy-to-device-machine"]], "2. The lack of cloudpickle on device
machine caused the RPC server can\u2019t be launched.": [[40,
"the-lack-of-cloudpickle-on-devi [...]
\ No newline at end of file
diff --git a/docs/sg_execution_times.html b/docs/sg_execution_times.html
index 4cbdafb04fd..7353ec1b63e 100644
--- a/docs/sg_execution_times.html
+++ b/docs/sg_execution_times.html
@@ -294,7 +294,7 @@
<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>00:40.911</strong> total execution time for 11 files <strong>from
all galleries</strong>:</p>
+<p><strong>00:41.202</strong> total execution time for 11 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" />
@@ -316,35 +316,35 @@ $(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>00:32.321</p></td>
+<td><p>00:32.768</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>00:06.041</p></td>
+<td><p>00:05.937</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><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>00:00.670</p></td>
+<td><p>00:00.653</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-odd"><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>00:00.573</p></td>
+<td><p>00:00.580</p></td>
<td><p>0.0</p></td>
</tr>
<tr class="row-even"><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>00:00.495</p></td>
+<td><p>00:00.445</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_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>00:00.292</p></td>
+<td><p>00:00.295</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>00:00.172</p></td>
+<td><p>00:00.173</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>00:00.170</p></td>
+<td><p>00:00.173</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_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>
