Update torchao api reference and add contributor guide #1255
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1255
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit f10990a with merge base f96e5ec ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jerryzh168
requested review from
drisspg,
HDCharles,
msaroufim,
andrewor14,
jcaip and
jainapurva
jerryzh168
added
the
topic: documentation
drisspg
reviewed
Nov 8, 2024
drisspg
reviewed
Nov 8, 2024
torchao/quantization/linear_activation_weight_observed_tensor.py
Outdated
Show resolved
Hide resolved
drisspg
reviewed
Nov 8, 2024
Summary: 1. updated torchao api reference for quantization to include the APIs we want to expose, renamed torchao/quantization/linear_activation_weight_observer.py and removed the safe_int_mm and int_scaled_matmul from quant_primitives.py 2. added pytorch#391 to torchao docs Test Plan: CI Reviewers: Subscribers: Tasks: Tags:
jerryzh168
force-pushed
the
update-docs
branch
from
3fbab7d to
6ed99de
Compare
drisspg
approved these changes
Nov 13, 2024
jerryzh168
force-pushed
the
update-docs
branch
from
6ed99de to
2b0f78b
Compare
andrewor14
approved these changes
Nov 13, 2024
sunjiweiswift
pushed a commit
to sunjiweiswift/ao
that referenced
this pull request
Nov 25, 2024
* Update torchao api reference and add contributor guide Summary: 1. updated torchao api reference for quantization to include the APIs we want to expose, renamed torchao/quantization/linear_activation_weight_observer.py and removed the safe_int_mm and int_scaled_matmul from quant_primitives.py 2. added pytorch#391 to torchao docs Test Plan: CI Reviewers: Subscribers: Tasks: Tags: * format * typo * renaming * comma * format * comments
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
* feat(granite): Add support for finding weight mapping files with other names Branch: GraniteCodeSupport Signed-off-by: Gabe Goodhart <[email protected]> * feat(granite): Add support for loading state_dict from safetensors Branch: GraniteCodeSupport Signed-off-by: Gabe Goodhart <[email protected]> * feat(safetensors): Use model_info to determine whether to download pth or safetensors The logic here will prefer pth over safetensors unless the model's config explicitly states a preference for safetensors over pth. If only one of the two is found, the download will use whichever is present. Branch: GraniteCodeSupport Signed-off-by: Gabe Goodhart <[email protected]> --------- Signed-off-by: Gabe Goodhart <[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.
Summary:
For torchao docs, I think we can include:
(1) API Reference (for modeling users)
(2) contributor guide (for researchers/developers)
(3) Tutorials (for modeling users)
for major feature announcement etc. users should refer to torchao repo README and release notes
Test Plan:
CI
Reviewers:
Subscribers:
Tasks:
Tags: