Promote pre-set spec.mem_id to AbsolutePlacementConstraint. (#18480)#18480
Open
hsharma35 wants to merge 1 commit intopytorch:mainfrom
Open
Promote pre-set spec.mem_id to AbsolutePlacementConstraint. (#18480)#18480hsharma35 wants to merge 1 commit intopytorch:mainfrom
hsharma35 wants to merge 1 commit intopytorch:mainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18480
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 2 Unrelated FailuresAs of commit 0deb43e with merge base a951e1b ( NEW FAILURE - The following job has failed:
BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
Contributor
|
@hsharma35 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D95413373. |
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Mar 24, 2026
…18480) Summary: In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g. planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass) are promoted to AbsolutePlacementConstraint before the solver runs. The planner then assigns only the offset within that tier, leaving mem_id intact. Specs that already have an explicit AbsolutePlacementConstraint are not double-promoted — the existing constraint wins. Adds test target test_memory_planning_algo with 5 regression tests: - unpinned spec placed freely in mem_id=1 - pinned spec stays in the requested tier - two specs pinned to the same tier get non-overlapping offsets - unpinned peers of pinned specs are not forced into the pinned tier - an externally-set AbsolutePlacementConstraint overrides spec.mem_id Differential Revision: D95413373
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Mar 24, 2026
…18480) Summary: In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g. planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass) are promoted to AbsolutePlacementConstraint before the solver runs. The planner then assigns only the offset within that tier, leaving mem_id intact. Specs that already have an explicit AbsolutePlacementConstraint are not double-promoted — the existing constraint wins. Adds test target test_memory_planning_algo with 5 regression tests: - unpinned spec placed freely in mem_id=1 - pinned spec stays in the requested tier - two specs pinned to the same tier get non-overlapping offsets - unpinned peers of pinned specs are not forced into the pinned tier - an externally-set AbsolutePlacementConstraint overrides spec.mem_id Differential Revision: D95413373
meta-codesync
bot
changed the title
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Mar 25, 2026
…18480) Summary: In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g. planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass) are promoted to AbsolutePlacementConstraint before the solver runs. The planner then assigns only the offset within that tier, leaving mem_id intact. Specs that already have an explicit AbsolutePlacementConstraint are not double-promoted — the existing constraint wins. Adds test target test_memory_planning_algo with 5 regression tests: - unpinned spec placed freely in mem_id=1 - pinned spec stays in the requested tier - two specs pinned to the same tier get non-overlapping offsets - unpinned peers of pinned specs are not forced into the pinned tier - an externally-set AbsolutePlacementConstraint overrides spec.mem_id Differential Revision: D95413373
hsharma35
force-pushed
the
export-D95413373
branch
from
24462e6 to
c009c00
Compare
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Mar 25, 2026
…18480) Summary: In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g. planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass) are promoted to AbsolutePlacementConstraint before the solver runs. The planner then assigns only the offset within that tier, leaving mem_id intact. Specs that already have an explicit AbsolutePlacementConstraint are not double-promoted — the existing constraint wins. Adds test target test_memory_planning_algo with 5 regression tests: - unpinned spec placed freely in mem_id=1 - pinned spec stays in the requested tier - two specs pinned to the same tier get non-overlapping offsets - unpinned peers of pinned specs are not forced into the pinned tier - an externally-set AbsolutePlacementConstraint overrides spec.mem_id Differential Revision: D95413373
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Mar 25, 2026
…18480) Summary: In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g. planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass) are promoted to AbsolutePlacementConstraint before the solver runs. The planner then assigns only the offset within that tier, leaving mem_id intact. Specs that already have an explicit AbsolutePlacementConstraint are not double-promoted — the existing constraint wins. Adds test target test_memory_planning_algo with 5 regression tests: - unpinned spec placed freely in mem_id=1 - pinned spec stays in the requested tier - two specs pinned to the same tier get non-overlapping offsets - unpinned peers of pinned specs are not forced into the pinned tier - an externally-set AbsolutePlacementConstraint overrides spec.mem_id Differential Revision: D95413373
hsharma35
force-pushed
the
export-D95413373
branch
2 times, most recently
from
5a4dec9 to
2ab5e79
Compare
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Mar 25, 2026
…18480) Summary: Pull Request resolved: pytorch#18480 In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g. planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass) are promoted to AbsolutePlacementConstraint before the solver runs. The planner then assigns only the offset within that tier, leaving mem_id intact. Specs that already have an explicit AbsolutePlacementConstraint are not double-promoted — the existing constraint wins. Adds test target test_memory_planning_algo with 5 regression tests: - unpinned spec placed freely in mem_id=1 - pinned spec stays in the requested tier - two specs pinned to the same tier get non-overlapping offsets - unpinned peers of pinned specs are not forced into the pinned tier - an externally-set AbsolutePlacementConstraint overrides spec.mem_id Differential Revision: D95413373
meta-codesync
bot
changed the title
hsharma35
force-pushed
the
export-D95413373
branch
from
2ab5e79 to
7b95a4b
Compare
meta-codesync
bot
changed the title
hsharma35
force-pushed
the
export-D95413373
branch
from
7b95a4b to
2fba64b
Compare
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Mar 25, 2026
…18480) Summary: In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g. planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass) are promoted to AbsolutePlacementConstraint before the solver runs. The planner then assigns only the offset within that tier, leaving mem_id intact. Specs that already have an explicit AbsolutePlacementConstraint are not double-promoted — the existing constraint wins. Adds test target test_memory_planning_algo with 5 regression tests: - unpinned spec placed freely in mem_id=1 - pinned spec stays in the requested tier - two specs pinned to the same tier get non-overlapping offsets - unpinned peers of pinned specs are not forced into the pinned tier - an externally-set AbsolutePlacementConstraint overrides spec.mem_id This is Milestone 6 of the planned-temporaries feature. Differential Revision: D95413373
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Mar 26, 2026
…18480) Summary: In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g. planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass) are promoted to AbsolutePlacementConstraint before the solver runs. The planner then assigns only the offset within that tier, leaving mem_id intact. Specs that already have an explicit AbsolutePlacementConstraint are not double-promoted — the existing constraint wins. Adds test target test_memory_planning_algo with 5 regression tests: - unpinned spec placed freely in mem_id=1 - pinned spec stays in the requested tier - two specs pinned to the same tier get non-overlapping offsets - unpinned peers of pinned specs are not forced into the pinned tier - an externally-set AbsolutePlacementConstraint overrides spec.mem_id This is Milestone 6 of the planned-temporaries feature. Differential Revision: D95413373
hsharma35
force-pushed
the
export-D95413373
branch
from
2fba64b to
5fe0082
Compare
…18480) Summary: Pull Request resolved: pytorch#18480 In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g. planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass) are promoted to AbsolutePlacementConstraint before the solver runs. The planner then assigns only the offset within that tier, leaving mem_id intact. Specs that already have an explicit AbsolutePlacementConstraint are not double-promoted — the existing constraint wins. Adds test target test_memory_planning_algo with 5 regression tests: - unpinned spec placed freely in mem_id=1 - pinned spec stays in the requested tier - two specs pinned to the same tier get non-overlapping offsets - unpinned peers of pinned specs are not forced into the pinned tier - an externally-set AbsolutePlacementConstraint overrides spec.mem_id This is Milestone 6 of the planned-temporaries feature. Differential Revision: D95413373
hsharma35
force-pushed
the
export-D95413373
branch
from
5fe0082 to
0deb43e
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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:
In plan_with_constraints(), specs that arrive with a pre-set mem_id (e.g.
planned-temporary alloc nodes whose spec.mem_id is pinned by the AOT pass)
are promoted to AbsolutePlacementConstraint before the solver runs. The
planner then assigns only the offset within that tier, leaving mem_id intact.
Specs that already have an explicit AbsolutePlacementConstraint are not
double-promoted — the existing constraint wins.
Adds test target test_memory_planning_algo with 5 regression tests:
This is Milestone 6 of the planned-temporaries feature.
Differential Revision: D95413373