[ET Device Support] Device-aware memory planning: separate buffers per device type#18375
Merged
Merged
Conversation
…r device type Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/) [ghstack-poisoned]
This was referenced Mar 20, 2026
Merged
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18375
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Mar 20, 2026
meta-cla
Bot
added
the
CLA Signed
This was referenced Mar 19, 2026
Gasoonjia
added a commit
that referenced
this pull request
Mar 20, 2026
…r device type Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/) ghstack-source-id: 355133801 Pull Request resolved: #18375
This PR needs a
|
… buffers per device type" Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/) [ghstack-poisoned]
This was referenced Mar 24, 2026
This was referenced Mar 24, 2026
Merged
… buffers per device type" Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/) [ghstack-poisoned]
… buffers per device type" Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/) [ghstack-poisoned]
This was referenced Apr 8, 2026
digantdesai
approved these changes
Apr 15, 2026
Contributor
digantdesai
left a comment
digantdesai
left a comment
There was a problem hiding this comment.
Review automatically exported from Phabricator review in Meta.
JacobSzwejbka
requested changes
Apr 29, 2026
Contributor
JacobSzwejbka
left a comment
JacobSzwejbka
left a comment
There was a problem hiding this comment.
Review automatically exported from Phabricator review in Meta.
… buffers per device type" Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/) [ghstack-poisoned]
JacobSzwejbka
approved these changes
May 8, 2026
… buffers per device type" Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/) [ghstack-poisoned]
… buffers per device type" Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/) [ghstack-poisoned]
… buffers per device type" Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/) [ghstack-poisoned]
This was referenced May 12, 2026
Gasoonjia
added a commit
that referenced
this pull request
May 12, 2026
…stry (#19496) Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #18474 * #18473 * #18472 * #18375 * #19497 * __->__ #19496 This diff introduces the `DeviceAllocator` abstract interface and `DeviceAllocatorRegistry` for device-specific memory allocation. This is a foundational abstraction that enables the runtime to dispatch memory operations to the appropriate device backend other than CPU (CUDA, etc.). **DeviceAllocator interface provides:** - `allocate()` / `deallocate()` - Dynamic device memory allocation - `copy_host_to_device()` / `copy_device_to_host()` - Data transfer between host and device - `device_type()` - Returns the device type this allocator handles **DeviceAllocatorRegistry provides:** - Singleton registry mapping DeviceType → DeviceAllocator - `register_allocator()` / `get_allocator()` methods - Fixed-size array indexed by device type (no dynamic allocation, embedded-friendly) **Design notes:** - Registry stores raw pointers (non-owning) - allocators are expected to be singletons with static lifetime - Follows ExecuTorch's embedded-first philosophy (no std::unique_ptr, no heap allocation in registry) - Convenience free functions `register_device_allocator()` and `get_device_allocator()` for ease of use Differential Revision: [D93635656](https://our.internmc.facebook.com/intern/diff/D93635656/)
Gasoonjia
added a commit
that referenced
this pull request
May 12, 2026
…vice mapping (#19497) Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #18474 * #18473 * #18472 * #18375 * __->__ #19497 * #19496 Adds the NonConstBufferDevice table to the FlatBuffer schema (program.fbs) and the corresponding Python dataclass to schema.py. This enables mapping each non-constant planned memory buffer to a specific device type (CPU, CUDA, etc.). The field is optional and absent for CPU-only programs, ensuring zero binary size regression. Differential Revision: [D97335597](https://our.internmc.facebook.com/intern/diff/D97335597/)
Gasoonjia
had a problem deploying
to
cherry-pick-bot
GitHub Actions
Failure
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
3 participants
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 (oldest at bottom):
Extends memory planning to separate device tensors from CPU tensors into distinct
memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific
mem_ids before the greedy/naive algorithm runs, ensuring they get planned into
independent memory buffers that never share space with CPU tensors.
Differential Revision: D97447105