Repository navigation
[executorch][cuda] Let the CUDA delegate drive the off-graph KV step - #23294
Merged
Merged
Conversation
Pull Request resolved: #22815 Lower the neutral `kvcache::update_and_attend` contract to runtime-bound private tensors, retain their logical metadata without serializing payloads, and allow the weight loader to defer those bindings. Add validation for manifests and storage omission. Authored with Codex. ghstack-source-id: 439161249 @exported-using-ghexport Differential Revision: [D119571985](https://our.internmc.facebook.com/intern/diff/D119571985/)
Pull Request resolved: #22816 Own dense flat and ring KV allocations in the CUDA runtime, grow flat caches geometrically with stream-ordered preservation, rebind AOTI pointers, and expose reset and memory metrics for the single-session path. Derive allocation size, growth-copy pitch, metrics, and AOTI descriptors from a configurable storage dtype; BF16 remains the default. Authored with Codex. ghstack-source-id: 439161268 @exported-using-ghexport Differential Revision: [D119571986](https://our.internmc.facebook.com/intern/diff/D119571986/)
Pull Request resolved: #22989 The runner currently calls prepare_step/commit_step on CudaKVCache, which puts a backend face in the runner's hands. The delegate is the natural owner: it already runs on the host immediately before and after the compiled program, and that is the only point where storage can grow and be rebound before the kernels read it. The one thing the delegate cannot work out for itself is how many tokens a step writes. Lowering compiles the cache op away, so at runtime there is only compiled code over pre-bound memory and nothing calls back out. The export side knows the width from its own signature, so it declares where to find it as an "input_index:dim" compile spec, and the delegate reads that input's extent -- shape metadata only, never contents, which are on device. Committing from here also pairs the two halves on every exit: a run that fails never advances the cache past tokens the kernels did not write. ghstack-source-id: 439161280 @exported-using-ghexport Differential Revision: [D121131873](https://our.internmc.facebook.com/intern/diff/D121131873/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/23294
Note: Links to docs will display an error until the docs builds have been completed. ❌ 67 Pending, 2 Unclassified FailuresAs of commit cb538e9 with merge base 7cfcde7 ( UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Gasoonjia
approved these changes
Oct 1, 2026
This PR needs a
|
This branch was successfully deployed
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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #22989 by @Gasoonjia
^ Please use this as the source of truth for the PR details, comments, and reviews
ghstack PR base: https://github.com/pytorch/executorch/tree/gh/gasoonjia/191/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/191/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/gasoonjia/186/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/191/orig
Differential Revision: D121131873
@diff-train-skip-merge