[Docs][torch.compile] NNCF quantization/compression #27934
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
daniil-lyakhov
force-pushed
the
dl/docs/torch_compile_nncf
branch
4 times, most recently
from
212a24a to
a39e498
Compare
ravi9
reviewed
Dec 5, 2024
daniil-lyakhov
force-pushed
the
dl/docs/torch_compile_nncf
branch
2 times, most recently
from
44f5476 to
193ec5c
Compare
ravi9
reviewed
Dec 6, 2024
| TorchServe is a performant, flexible, and easy to use tool for serving PyTorch models in production. For more information on the details of TorchServe, | ||
| you can refer to `TorchServe github repository. <https://github.com/pytorch/serve>`__. With OpenVINO ``torch.compile`` integration into TorchServe you can serve | ||
| PyTorch models in production and accelerate them with OpenVINO on various Intel hardware. Detailed instructions on how to use OpenVINO with TorchServe are | ||
| available in `TorchServe examples. <https://github.com/pytorch/serve/tree/master/examples/pt2/torch_compile_openvino>`__ |
There was a problem hiding this comment.
Hi @daniil-lyakhov : I was thinking here, as we mention about general TorchServe examples..
ravi9
reviewed
Dec 6, 2024
rkazants
reviewed
Dec 8, 2024
rkazants
reviewed
Dec 8, 2024
rkazants
reviewed
Dec 8, 2024
| NNCF unlocks the full potential of low-precision OpenVINO kernels due to quantizers placement designed specifically for the OpenVINO. | ||
| Advanced algorithms like ``SmoothQuant`` or ``BiasCorrection`` allows furher metrics improvement minimizing the outputs discrepancy between the original and compressed models. | ||
| For further details, please see the `documentation <https://docs.openvino.ai/2024/openvino-workflow/model-optimization.html>`__ | ||
| and a `tutorial <https://github.com/daniil-lyakhov/nncf/tree/develop/examples/post_training_quantization/torch_fx/resnet18>`__. |
There was a problem hiding this comment.
I think link is incorrect. it should be official main repo
There was a problem hiding this comment.
My bad, fixed, thanks!
daniil-lyakhov
force-pushed
the
dl/docs/torch_compile_nncf
branch
from
d500073 to
8546fe9
Compare
daniil-lyakhov
force-pushed
the
dl/docs/torch_compile_nncf
branch
from
8546fe9 to
c921d4d
Compare
alexsu52
reviewed
Dec 13, 2024
daniil-lyakhov
requested review from
kblaszczak-intel
and removed request for
a team
alexsu52
reviewed
Dec 16, 2024
daniil-lyakhov
force-pushed
the
dl/docs/torch_compile_nncf
branch
from
c15ea7d to
a2e8e0b
Compare
MaximProshin
approved these changes
Dec 17, 2024
daniil-lyakhov
force-pushed
the
dl/docs/torch_compile_nncf
branch
2 times, most recently
from
8bd6753 to
7cb0446
Compare
daniil-lyakhov
force-pushed
the
dl/docs/torch_compile_nncf
branch
from
7cb0446 to
1a8a556
Compare
alexsu52
approved these changes
Dec 18, 2024
rkazants
approved these changes
Dec 18, 2024
kblaszczak-intel
approved these changes
Dec 18, 2024
github-merge-queue bot
pushed a commit
that referenced
this pull request
Dec 18, 2024
port: #27934 Co-authored-by: Daniil Lyakhov <[email protected]>
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.
https://openvino-doc.iotg.sclab.intel.com/nncf-docs/openvino-workflow/torch-compile.html#model-quantization-and-weights-compression
Details:
torch.compiledocumentation