<EXPERIMENTAL - DO NOT REVIEW> DYNAMIC_UNBOUND support for portable runtime: lazy KV cache allocation#18350
Draft
<EXPERIMENTAL - DO NOT REVIEW> DYNAMIC_UNBOUND support for portable runtime: lazy KV cache allocation#18350
Conversation
Enable DYNAMIC_UNBOUND tensors in the portable runtime, allowing KV cache buffers to be dynamically managed rather than statically memory-planned. This is the architectural foundation for pay-as-you-go memory allocation in ExecuTorch LLM inference. Core changes: - DynamicAllocator interface with allocate/reallocate/free - PalDynamicAllocator default impl (PAL-backed, 2x growth policy) - TrackingDynamicAllocator for memory stats observability - MemoryManager gains 4th slot for DynamicAllocator (backward compatible) - TensorImpl gains dynamic_allocator_ and capacity_bytes_ fields - TensorImpl::internal_resize_contiguous handles DYNAMIC_UNBOUND resize - tensor_parser_portable.cpp: remove DYNAMIC_UNBOUND rejection, wire up allocator at load time for tensors with no memory-planned data - method.cpp: FreeCall frees dynamic memory; destructor cleans up all - Module API auto-creates PalDynamicAllocator (DYNAMIC_UNBOUND just works) Export changes: - MarkDynamicUnboundPass marks KV cache buffers as DYNAMIC_UNBOUND - --lazy_kv_cache flag for Llama export Co-authored-by: Claude <noreply@anthropic.com>
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18350
Note: Links to docs will display an error until the docs builds have been completed. ❌ 9 New Failures, 1 Unrelated FailureAs of commit f0b5b5f with merge base 02bad9d ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
psiddh
changed the title
This PR needs a
|
digantdesai
reviewed
Mar 20, 2026
| default=False, | ||
| help="Mark KV cache buffers as DYNAMIC_UNBOUND so they are allocated " | ||
| "lazily at runtime instead of at load time. Reduces initial memory " | ||
| "usage when max_context_length is large.", |
Contributor
There was a problem hiding this comment.
is this because we do actually touch the full memory during attention?
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
2 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.
Enable DYNAMIC_UNBOUND tensors in the portable runtime, allowing KV cache buffers to be dynamically managed rather than statically memory-planned. This is the architectural foundation for pay-as-you-go memory allocation in ExecuTorch LLM inference.
Core changes:
Export changes:
Summary
[PLEASE REMOVE] See CONTRIBUTING.md's Pull Requests for ExecuTorch PR guidelines.
[PLEASE REMOVE] If this PR closes an issue, please add a
Fixes #<issue-id>line.[PLEASE REMOVE] If this PR introduces a fix or feature that should be the upcoming release notes, please add a "Release notes: " label. For a list of available release notes labels, check out CONTRIBUTING.md's Pull Requests.
Test plan
[PLEASE REMOVE] How did you test this PR? Please write down any manual commands you used and note down tests that you have written if applicable.