-
Notifications
You must be signed in to change notification settings - Fork 21.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Quant][docs] Add README for BackendConfig #86523
Conversation
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/86523
Note: Links to docs will display an error until the docs builds have been completed. ✅ No Failures, 2 PendingAs of commit 14a8c98: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: a5aedd9ade7cb8965534a84f443334ba97fb7581 Pull Request resolved: #86523
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: a5aedd9ade7cb8965534a84f443334ba97fb7581 Pull Request resolved: #86523
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: a1625ab1c66779c661e9d7aad2746bd3a48c366f Pull Request resolved: #86523
.set_backend_pattern_config(linear_config) \ | ||
.set_backend_pattern_config(conv_relu_config) | ||
``` | ||
#### set_observation_type |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I feel some of these should be moved to docstrings for the API?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we should discuss about the goal for the README, my current understanding is that the README should describe the design decisions and how it is implemented
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think a key thing would be to avoid duplication. Either we should have these examples in docstrings or here, but not in both places. If it's duplicated the risk of it being outdated increases.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I do feel like what is in this file now would fit more naturally in documentation, this seems to be documentation for users of BackendConfig, not necessarily developers of AO code.
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: a1625ab1c66779c661e9d7aad2746bd3a48c366f Pull Request resolved: #86523
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: c770e50a9cbd339210ac3de1fff61f225135921e Pull Request resolved: #86523
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks!
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: cbf1914e40f0e32267bb2eb21491c306eb893258 Pull Request resolved: #86523
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: 10b463ba46ec5d6d6d96188fe306f7b22743a310 Pull Request resolved: #86523
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: 99346bd2b4019670344e73ba1d6c61ead18b161a Pull Request resolved: #86523
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: 99346bd2b4019670344e73ba1d6c61ead18b161a Pull Request resolved: #86523
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: 45bf53809e3067a4afa0bc3c057c042b631b2761 Pull Request resolved: #86523
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo [ghstack-poisoned]
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo ghstack-source-id: 9af2b16a57be92a37c27ca0183b6e362276c4305 Pull Request resolved: #86523
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo Pull Request resolved: pytorch#86523 Approved by: https://github.com/jerryzh168
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo Pull Request resolved: pytorch#86523 Approved by: https://github.com/jerryzh168
Summary: This adds a README for `torch.ao.quantization.backend_config` that describes both the high level motivation and the specifications of the BackendConfig API. Reviewers: jerryzh168, vkuzo Subscribers: jerryzh168, vkuzo Pull Request resolved: pytorch#86523 Approved by: https://github.com/jerryzh168
Stack from ghstack (oldest at bottom):
Summary: This adds a README for
torch.ao.quantization.backend_config
that describes both the high level motivation and the specifications
of the BackendConfig API.
Reviewers: jerryzh168, vkuzo
Subscribers: jerryzh168, vkuzo