-
Notifications
You must be signed in to change notification settings - Fork 22.2k
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] Bug fix #107899
[Quant] Bug fix #107899
Conversation
Summary: When two layers are quantized differently, observer map update updates map for key (observed_node, node), whereas it should really be (original_input, node) Test Plan: Test in the next diff adds a test where it otherwise fails Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/107899
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit b25f1b6 with merge base 0f1a225 (): This comment was automatically generated by Dr. CI and updates every 15 minutes. |
@kimishpatel has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@@ -92,6 +92,16 @@ def _maybe_insert_input_observer_for_arg_or_kwarg( | |||
new_obs_node = _insert_obs_or_fq( | |||
arg, arg_as_input_act_obs_or_fq, model, named_modules, model.graph) # type: ignore[arg-type] | |||
new_arg = new_obs_node | |||
# When quantizing two layers with different configs we can have |
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.
can you add a test for this? surprised that this is not caught earlier..
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.
so didnt add separate test because the PR after this one fails for exactly this reason. Also we havent tested quantizing a different layers with different configs (which is what the next diff does). Hence did not catch it.
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.
OK sounds good
Summary: When two layers are quantized differently, observer map update updates map for key (observed_node, node), whereas it should really be (original_input, node) Test Plan: Test in the next diff adds a test where it otherwise fails Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D48663145](https://our.internmc.facebook.com/intern/diff/D48663145) [ghstack-poisoned]
Summary: When two layers are quantized differently, observer map update updates map for key (observed_node, node), whereas it should really be (original_input, node) Test Plan: Test in the next diff adds a test where it otherwise fails Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D48663145](https://our.internmc.facebook.com/intern/diff/D48663145) [ghstack-poisoned]
Summary: When two layers are quantized differently, observer map update updates map for key (observed_node, node), whereas it should really be (original_input, node) Test Plan: Test in the next diff adds a test where it otherwise fails Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D48663145](https://our.internmc.facebook.com/intern/diff/D48663145) [ghstack-poisoned]
@kimishpatel has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
3 similar comments
@kimishpatel has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@kimishpatel has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@kimishpatel has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: When two layers are quantized differently, observer map update updates map for key (observed_node, node), whereas it should really be (original_input, node) Test Plan: Test in the next diff adds a test where it otherwise fails Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D48663145](https://our.internmc.facebook.com/intern/diff/D48663145) [ghstack-poisoned]
@kimishpatel has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
1 similar comment
@kimishpatel has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: During convert step observers are first replaced by Q-DQ pair. In some scenarios like following output DQ has a fan out. ---> OP2 -> Q -> DQ / OP -> Q -> DQ - \ ---> OP3 -> Q -> DQ If either op OP2 or OP3 are configured to be quantized, then the input is expected to quantized. In this case quantized equivalent of some pattern, that quantizer asked to be quantized, should look like: [DQ -> {pattern} -> Q]. However, in scenario like above where DQ node is shared between multiple "quantized" patterns, boundary of "quantized" pattern is not clear because DQ now belongs to multiple quantized patterns. This poses challenge for: - Porting metadata: which "quantized" partition this DQ node belongs - Quantized representation, equivalently, needs to identify self-contained quantized pattern that is replaced by its equivalent pattern that captures compute in the quantized precision. Test Plan: test_duplicate_dq_pass Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D48663147](https://our.internmc.facebook.com/intern/diff/D48663147) Pull Request resolved: #107900 Approved by: https://github.com/jerryzh168, https://github.com/andrewor14, https://github.com/leslie-fang-intel ghstack dependencies: #107105, #107106, #107899
…107107) Summary: This diff adds adding metadata to q-dq nodes by inferring the quatization intent from node annotations. Annotations on the node are way for user to specify how a node or subgraph is supposed to be quantized. We continue to use that information to copy metadata on Q/DQ node from appropriate nodes. Test Plan: Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D48488416](https://our.internmc.facebook.com/intern/diff/D48488416) Pull Request resolved: #107107 Approved by: https://github.com/jerryzh168 ghstack dependencies: #107105, #107106, #107899, #107900
Stack from ghstack (oldest at bottom):
Summary:
When two layers are quantized differently, observer map update updates
map for key (observed_node, node), whereas it should really be
(original_input, node)
Test Plan:
Test in the next diff adds a test where it otherwise fails
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D48663145