[quant] Make PerChannelMinMaxObserver scriptable using torch.jit.ignore
#29416
Conversation
This file contains hidden or 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
…ore` Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 9, 2019
Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls - add support of folding for prepacked per channel quantized weight Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
This was referenced Nov 9, 2019
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 9, 2019
…ntization in graph mode" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls - add support of folding for prepacked per channel quantized weight Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 9, 2019
…ph mode" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls - add support of folding for prepacked per channel quantized weight Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 13, 2019
…ntization in graph mode" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls - add support of folding for prepacked per channel quantized weight Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 13, 2019
…ph mode" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls - add support of folding for prepacked per channel quantized weight Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 13, 2019
…ntization in graph mode" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls - add support of folding for prepacked per channel quantized weight Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 13, 2019
…ph mode" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls - add support of folding for prepacked per channel quantized weight Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 13, 2019
…ntization in insert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 13, 2019
…ert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 13, 2019
…equant and fold_prepack Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: ghstack-source-id: ea7a8fb Pull Request resolved: #29492
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 15, 2019
…ntization in insert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 15, 2019
…ert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 15, 2019
…ntization in insert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 15, 2019
…ert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 18, 2019
…ntization in insert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 18, 2019
…ert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: [ghstack-poisoned]
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 18, 2019
…ntization in insert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: Differential Revision: [D18580444](https://our.internmc.facebook.com/intern/diff/D18580444) [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 18, 2019
…ert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: Differential Revision: [D18580444](https://our.internmc.facebook.com/intern/diff/D18580444) [ghstack-poisoned]
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: Differential Revision: [D18580906](https://our.internmc.facebook.com/intern/diff/D18580906) [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 19, 2019
…ntization in insert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: Differential Revision: [D18580444](https://our.internmc.facebook.com/intern/diff/D18580444) [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 19, 2019
…ert_quant_dequant and fold_prepack" Summary: Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Reviewers: mvz Subscribers: Tasks: Tags: Differential Revision: [D18580444](https://our.internmc.facebook.com/intern/diff/D18580444) [ghstack-poisoned]
facebook-github-bot
pushed a commit
that referenced
this pull request
Nov 19, 2019
…pack (#29492) Summary: Pull Request resolved: #29492 Previously graph mode quantization only works for per tensor quantization, this PR added support for per channel quantization as well, changes include - insert per channel quantization calls(insert_quant_dequant) - add support of folding for prepacked per channel quantized weight (fold_prepack) Test Plan: test is not possible until we can script PerChannelObserver, which comes in #29416 we'll add test in a separate PR after that. Imported from OSS Differential Revision: D18580444 fbshipit-source-id: 347c07f201648ec49f070523642a9170278f8aa4
…rch.jit.ignore`" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: Differential Revision: [D18580906](https://our.internmc.facebook.com/intern/diff/D18580906) [ghstack-poisoned]
|
This pull request has been merged in b2291d4. |
|
This pull request has been merged in b2291d4. |
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.
Stack from ghstack:
torch.jit.ignore#29416 [quant] Make PerChannelMinMaxObserver scriptable usingtorch.jit.ignoreSummary:
att
Test Plan:
python test/test_quantization.py
Reviewers:
pt1quant
Subscribers:
Tasks:
Tags:
Differential Revision: D18580906