Update 0.10.0 docs & refactor docs structure #167
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
/gen-doc |
|
Documentation generated by PR-167 successfully! |
|
/gen-doc |
|
Documentation generated by PR-167 successfully! |
furiosamg
force-pushed
the
update-docs-0.10.0
branch
2 times, most recently
from
eee198d to
32876b1
Compare
furiosamg
force-pushed
the
update-docs-0.10.0
branch
from
32876b1 to
f93dfff
Compare
|
i18n 추가하려고 했는데,
|
furiosamg
force-pushed
the
update-docs-0.10.0
branch
from
f93dfff to
b28d3a4
Compare
|
/gen-doc |
furiosamg
changed the title
|
Documentation generated by PR-167 successfully! |
furiosamg
force-pushed
the
update-docs-0.10.0
branch
from
b28d3a4 to
5d93f29
Compare
|
/gen-doc |
|
Documentation generated by PR-167 successfully! |
furiosamg
force-pushed
the
update-docs-0.10.0
branch
from
4255188 to
f9f6ffb
Compare
|
/gen-doc |
|
Documentation generated by PR-167 successfully! |
furiosamg
force-pushed
the
update-docs-0.10.0
branch
from
f9f6ffb to
a68f1e8
Compare
Signed-off-by: Myeong-geun Shin <mg.shin@furiosa.ai>
Signed-off-by: Myeong-geun Shin <mg.shin@furiosa.ai>
Signed-off-by: Myeong-geun Shin <mg.shin@furiosa.ai>
|
/gen-doc |
|
Documentation generated by PR-167 successfully! |
Pip freeze result for allpip freeze resultaiobotocore==2.5.4 aiofiles==23.2.1 aiohttp==3.8.5 aiohttp-retry==2.8.3 aioitertools==0.11.0 aiosignal==1.3.1 amqp==5.1.1 annotated-types==0.5.0 antlr4-python3-runtime==4.9.3 appdirs==1.4.4 asttokens==2.4.0 async-timeout==4.0.3 asyncssh==2.13.2 atpublic==4.0 attrs==23.1.0 backcall==0.2.0 billiard==4.1.0 boto3==1.28.17 botocore==1.31.17 celery==5.3.4 certifi==2023.7.22 cffi==1.15.1 charset-normalizer==3.2.0 click==8.1.7 click-didyoumean==0.3.0 click-plugins==1.1.1 click-repl==0.3.0 cmake==3.27.5 colorama==0.4.6 comm==0.1.4 configobj==5.0.8 contourpy==1.1.1 cryptography==41.0.4 cycler==0.11.0 Cython==3.0.2 debugpy==1.8.0 decorator==5.1.1 dictdiffer==0.9.0 diskcache==5.6.3 distro==1.8.0 dpath==2.1.6 dulwich==0.21.6 dvc==3.22.1 dvc-data==2.16.3 dvc-http==2.30.2 dvc-objects==1.0.1 dvc-render==0.6.0 dvc-s3==2.23.0 dvc-studio-client==0.15.0 dvc-task==0.3.0 exceptiongroup==1.1.3 executing==1.2.0 fastjsonschema==2.18.0 filelock==3.12.4 flatten-dict==0.4.2 flufl.lock==7.1.1 fonttools==4.42.1 frozenlist==1.4.0 fsspec==2023.9.2 funcy==2.0 furiosa-common==0.10.0 furiosa-models @ file:///app furiosa-native-postprocess==0.9.0.dev0 furiosa-native-runtime==0.10.1 furiosa-quantizer==0.10.0 furiosa-quantizer-impl==0.10.0 furiosa-runtime==0.10.0 furiosa-tools==0.10.0 gitdb==4.0.10 GitPython==3.1.37 grandalf==0.8 hydra-core==1.3.2 idna==3.4 importlib-metadata==6.8.0 importlib-resources==6.1.0 iniconfig==2.0.0 ipykernel==6.25.2 ipython==8.15.0 iterative-telemetry==0.0.8 jedi==0.19.0 Jinja2==3.1.2 jmespath==1.0.1 jsonschema==4.19.1 jsonschema-specifications==2023.7.1 jupyter_client==8.3.1 jupyter_core==5.3.1 kiwisolver==1.4.5 kombu==5.3.2 lit==17.0.0rc4 markdown-it-py==3.0.0 MarkupSafe==2.1.3 matplotlib==3.8.0 matplotlib-inline==0.1.6 mdurl==0.1.2 mpmath==1.3.0 multidict==6.0.4 multipledispatch==1.0.0 nbclient==0.6.8 nbformat==5.9.2 nbmake==1.4.3 nest-asyncio==1.5.8 networkx==3.1 numpy==1.25.2 nvidia-cublas-cu11==11.10.3.66 nvidia-cuda-cupti-cu11==11.7.101 nvidia-cuda-nvrtc-cu11==11.7.99 nvidia-cuda-runtime-cu11==11.7.99 nvidia-cudnn-cu11==8.5.0.96 nvidia-cufft-cu11==10.9.0.58 nvidia-curand-cu11==10.2.10.91 nvidia-cusolver-cu11==11.4.0.1 nvidia-cusparse-cu11==11.7.4.91 nvidia-nccl-cu11==2.14.3 nvidia-nvtx-cu11==11.7.91 omegaconf==2.3.0 onnx==1.14.1 opencv-python-headless==4.8.0.76 orjson==3.9.7 packaging==23.1 pandas==2.0.3 parso==0.8.3 pathspec==0.11.2 pexpect==4.8.0 pickleshare==0.7.5 Pillow==10.0.1 platformdirs==3.10.0 pluggy==1.3.0 prompt-toolkit==3.0.39 protobuf==4.24.3 psutil==5.9.5 ptyprocess==0.7.0 pure-eval==0.2.2 py-cpuinfo==9.0.0 pyarrow==12.0.1 pycocotools==2.0.7 pycparser==2.21 pydantic==2.3.0 pydantic_core==2.6.3 pydot==1.4.2 pygit2==1.13.1 Pygments==2.16.1 pygtrie==2.5.0 pyparsing==3.1.1 pytest==7.4.2 pytest-asyncio==0.17.2 pytest-benchmark==4.0.0 python-dateutil==2.8.2 pytz==2023.3.post1 PyYAML==6.0.1 pyzmq==25.1.1 referencing==0.30.2 requests==2.31.0 rich==13.5.3 rpds-py==0.10.3 ruamel.yaml==0.17.32 ruamel.yaml.clib==0.2.7 s3fs==2023.9.2 s3transfer==0.6.2 scmrepo==1.3.1 shortuuid==1.0.11 shtab==1.6.4 six==1.16.0 smmap==5.0.1 sqltrie==0.7.0 stack-data==0.6.2 sympy==1.12 tabulate==0.9.0 tomli==2.0.1 tomlkit==0.12.1 torch==2.0.1 torchvision==0.15.2 tornado==6.3.3 tqdm==4.66.1 traitlets==5.10.0 triton==2.0.0 typing_extensions==4.8.0 tzdata==2023.3 urllib3==1.26.16 vine==5.0.0 voluptuous==0.13.1 wcwidth==0.2.6 wrapt==1.15.0 yarl==1.9.2 zc.lockfile==3.0.post1 zipp==3.17.0 |
|
add3e67 nits: import early, packaging stuffs correctly |
Pip freeze result for allpip freeze resultaiobotocore==2.5.4 aiofiles==23.2.1 aiohttp==3.8.5 aiohttp-retry==2.8.3 aioitertools==0.11.0 aiosignal==1.3.1 amqp==5.1.1 annotated-types==0.5.0 antlr4-python3-runtime==4.9.3 appdirs==1.4.4 asttokens==2.4.0 async-timeout==4.0.3 asyncssh==2.13.2 atpublic==4.0 attrs==23.1.0 backcall==0.2.0 billiard==4.1.0 boto3==1.28.17 botocore==1.31.17 celery==5.3.4 certifi==2023.7.22 cffi==1.15.1 charset-normalizer==3.2.0 click==8.1.7 click-didyoumean==0.3.0 click-plugins==1.1.1 click-repl==0.3.0 cmake==3.27.5 colorama==0.4.6 comm==0.1.4 configobj==5.0.8 contourpy==1.1.1 cryptography==41.0.4 cycler==0.11.0 Cython==3.0.2 debugpy==1.8.0 decorator==5.1.1 dictdiffer==0.9.0 diskcache==5.6.3 distro==1.8.0 dpath==2.1.6 dulwich==0.21.6 dvc==3.22.1 dvc-data==2.16.3 dvc-http==2.30.2 dvc-objects==1.0.1 dvc-render==0.6.0 dvc-s3==2.23.0 dvc-studio-client==0.15.0 dvc-task==0.3.0 exceptiongroup==1.1.3 executing==1.2.0 fastjsonschema==2.18.0 filelock==3.12.4 flatten-dict==0.4.2 flufl.lock==7.1.1 fonttools==4.42.1 frozenlist==1.4.0 fsspec==2023.9.2 funcy==2.0 furiosa-common==0.10.0 furiosa-models @ file:///app furiosa-native-postprocess==0.9.0.dev0 furiosa-native-runtime==0.10.1 furiosa-quantizer==0.10.0 furiosa-quantizer-impl==0.10.0 furiosa-runtime==0.10.0 furiosa-tools==0.10.0 gitdb==4.0.10 GitPython==3.1.37 grandalf==0.8 hydra-core==1.3.2 idna==3.4 importlib-metadata==6.8.0 importlib-resources==6.1.0 iniconfig==2.0.0 ipykernel==6.25.2 ipython==8.15.0 iterative-telemetry==0.0.8 jedi==0.19.0 Jinja2==3.1.2 jmespath==1.0.1 jsonschema==4.19.1 jsonschema-specifications==2023.7.1 jupyter_client==8.3.1 jupyter_core==5.3.1 kiwisolver==1.4.5 kombu==5.3.2 lit==17.0.0rc4 markdown-it-py==3.0.0 MarkupSafe==2.1.3 matplotlib==3.8.0 matplotlib-inline==0.1.6 mdurl==0.1.2 mpmath==1.3.0 multidict==6.0.4 multipledispatch==1.0.0 nbclient==0.6.8 nbformat==5.9.2 nbmake==1.4.3 nest-asyncio==1.5.8 networkx==3.1 numpy==1.25.2 nvidia-cublas-cu11==11.10.3.66 nvidia-cuda-cupti-cu11==11.7.101 nvidia-cuda-nvrtc-cu11==11.7.99 nvidia-cuda-runtime-cu11==11.7.99 nvidia-cudnn-cu11==8.5.0.96 nvidia-cufft-cu11==10.9.0.58 nvidia-curand-cu11==10.2.10.91 nvidia-cusolver-cu11==11.4.0.1 nvidia-cusparse-cu11==11.7.4.91 nvidia-nccl-cu11==2.14.3 nvidia-nvtx-cu11==11.7.91 omegaconf==2.3.0 onnx==1.14.1 opencv-python-headless==4.8.0.76 orjson==3.9.7 packaging==23.1 pandas==2.0.3 parso==0.8.3 pathspec==0.11.2 pexpect==4.8.0 pickleshare==0.7.5 Pillow==10.0.1 platformdirs==3.10.0 pluggy==1.3.0 prompt-toolkit==3.0.39 protobuf==4.24.3 psutil==5.9.5 ptyprocess==0.7.0 pure-eval==0.2.2 py-cpuinfo==9.0.0 pyarrow==12.0.1 pycocotools==2.0.7 pycparser==2.21 pydantic==2.3.0 pydantic_core==2.6.3 pydot==1.4.2 pygit2==1.13.1 Pygments==2.16.1 pygtrie==2.5.0 pyparsing==3.1.1 pytest==7.4.2 pytest-asyncio==0.17.2 pytest-benchmark==4.0.0 python-dateutil==2.8.2 pytz==2023.3.post1 PyYAML==6.0.1 pyzmq==25.1.1 referencing==0.30.2 requests==2.31.0 rich==13.5.3 rpds-py==0.10.3 ruamel.yaml==0.17.32 ruamel.yaml.clib==0.2.7 s3fs==2023.9.2 s3transfer==0.6.2 scmrepo==1.3.1 shortuuid==1.0.11 shtab==1.6.4 six==1.16.0 smmap==5.0.1 sqltrie==0.7.0 stack-data==0.6.2 sympy==1.12 tabulate==0.9.0 tomli==2.0.1 tomlkit==0.12.1 torch==2.0.1 torchvision==0.15.2 tornado==6.3.3 tqdm==4.66.1 traitlets==5.10.0 triton==2.0.0 typing_extensions==4.8.0 tzdata==2023.3 urllib3==1.26.16 vine==5.0.0 voluptuous==0.13.1 wcwidth==0.2.6 wrapt==1.15.0 yarl==1.9.2 zc.lockfile==3.0.post1 zipp==3.17.0 |
|
add3e67 nits: import early, packaging stuffs correctly |
|
/gen-doc |
|
Documentation generated by PR-167 successfully! |
hyunsik
reviewed
Oct 31, 2023
There was a problem hiding this comment.
quantize_and_compile_model.ipynb seems to need a brief description of this example. It's hard to understand how the quantization and model zoo is related to each other. Also, it would be great if you add links to the quantization section of SDK doc.
| @@ -0,0 +1,5 @@ | |||
| # Serving Example with furiosa-serving | |||
|
|
|||
There was a problem hiding this comment.
It seems to need at least a brief description. Also, it would be great if you add how to use furiosa-serving and its links.
There was a problem hiding this comment.
Add detailed page at 2bcdaf8
|
|
||
| - [Furiosa SDK - furiosa.runtime API Reference](https://furiosa-ai.github.io/docs/latest/en/api/python/furiosa.runtime.html) | ||
| - [Furiosa SDK - furiosa.runtime.sync.create_runner Reference](https://furiosa-ai.github.io/docs/latest/en/api/python/furiosa.runtime.html#furiosa.runtime.sync.Runtime) | ||
| - [Furiosa SDK - Tutorial and Code Examples](https://furiosa-ai.github.io/docs/latest/en/software/tutorials.html). |
There was a problem hiding this comment.
This update was necessary. This part looks great.
docs/model_object.md
Outdated
| In addition, a `Model` object has various metadata. The followings are all attributes belonging to a single `Model` object. | ||
| A Model object encompasses model artifacts, such as ONNX, TFLite, mapping from a tensor name to the tensor's min and max, and ENF. | ||
|
|
||
| The ENF format is specific to the FuriosaAI Compiler. |
There was a problem hiding this comment.
Most users would be not familiar with ENF. So, I've added a little bit more description for ENF.
Suggested change
| The ENF format is specific to the FuriosaAI Compiler. | |
| ENF is the serialization format of a compiled binary used in Furiosa SDK. |
There was a problem hiding this comment.
Applied in f771d98
docs/model_object.md
Outdated
|
|
||
| ## Inferencing with Session API | ||
| To create a Runner, pass the ENF binary obtained from the `model_source()` method of the model object to the `furiosa.runtime.sync.create_runner` function. If you prefer an asynchronous Runner, you can use the `furiosa.runtime.create_runner` function instead. Passing the pre-compiled ENF binary allows you to perform inference directly without the compilation process. Alternatively, you can also manually quantize and compile the original f32 model with the provided calibration range. |
There was a problem hiding this comment.
This is not a part that you changed. I revised this part to be more kind.
Suggested change
| To create a Runner, pass the ENF binary obtained from the `model_source()` method of the model object to the `furiosa.runtime.sync.create_runner` function. If you prefer an asynchronous Runner, you can use the `furiosa.runtime.create_runner` function instead. Passing the pre-compiled ENF binary allows you to perform inference directly without the compilation process. Alternatively, you can also manually quantize and compile the original f32 model with the provided calibration range. | |
| To create a Runner, you need to pass the ENF binary obtained from the `model_source()` method of the model object to the `furiosa.runtime.sync.create_runner` function. If you prefer an asynchronous Runner, you can use the `furiosa.runtime.create_runner` function instead. Passing the pre-compiled ENF binary allows you to perform inference directly without the compilation process. Alternatively, you can also manually quantize and compile the original f32 model with the provided calibration range. |
There was a problem hiding this comment.
Applied in f771d98
docs/model_object.md
Outdated
| At this stage, the compiler configuration can be specified. | ||
| To work with f32 source models, calibration and quantization are essential steps. | ||
| You can access pre-calibrated data directly from furiosa-models, simplifying the quantization process. | ||
| If you prefer manual quantization of the model, you can install the `furiosa-quantizer` package, available at this [package link](https://furiosa-ai.github.io/docs/latest/en/software/python-sdk.html#quantizer). |
There was a problem hiding this comment.
Suggested change
| If you prefer manual quantization of the model, you can install the `furiosa-quantizer` package, available at this [package link](https://furiosa-ai.github.io/docs/latest/en/software/python-sdk.html#quantizer). | |
| If you prefer a manual quantization step for a model, you can install the `furiosa-quantizer` package, available at this [package link](https://furiosa-ai.github.io/docs/latest/en/software/python-sdk.html#quantizer). |
There was a problem hiding this comment.
Applied in f771d98
|
/gen-doc |
|
Documentation generated by PR-167 successfully! |
furiosamg
force-pushed
the
update-docs-0.10.0
branch
from
2bcdaf8 to
100f66a
Compare
|
@hyunsik 리뷰 주신 부분들 반영했습니다. quantize & compile 문서도 더 적었습니다! |
furiosamg
changed the title
libc-furiosa
approved these changes
Nov 6, 2023
README.md
Outdated
| * [Furiosa SDK - Tutorial and Code Examples](https://furiosa-ai.github.io/docs/latest/en/software/tutorials.html) | ||
| * [Model object](https://furiosa-ai.github.io/furiosa-models/v0.10.0/model_object/) | ||
| * [Model List](https://furiosa-ai.github.io/furiosa-models/v0.10.0/#model_list) | ||
| * [Command Tool](https://furiosa-ai.github.io/furiosa-models/v0.10.0/command_line_tool/) |
There was a problem hiding this comment.
링크도 Command Line Tool로 변경해야할 것 같습니다.
Suggested change
| * [Command Tool](https://furiosa-ai.github.io/furiosa-models/v0.10.0/command_line_tool/) | |
| * [Command Line Tool](https://furiosa-ai.github.io/furiosa-models/v0.10.0/command_line_tool/) |
There was a problem hiding this comment.
감사합니다 c1aca86 에서 반영했습니다!
|
/gen-doc |
|
Documentation generated by PR-167 successfully! |
hyunsik
approved these changes
Nov 7, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.