Move torch.cond predicate non-persistent buffer to CPU #16378
Merged
+662
−7
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
Contributor
Author
|
Stack from ghstack (oldest at bottom): |
larryliu0820
requested review from
JacobSzwejbka,
SS-JIA,
cccclai,
digantdesai,
lucylq and
mergennachin
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16378
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (1 Unrelated Failure)As of commit 7e0e692 with merge base c5d66a5 ( UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
larryliu0820
added a commit
that referenced
this pull request
Dec 23, 2025
Avoid device-to-host memory copies when evaluating `torch.cond` predicates. When a GPU buffer (e.g., a KV cache `initialized` flag) is used as a predicate for `torch.cond`, the runtime must synchronize and copy the predicate value from GPU to CPU on every forward pass to evaluate the condition. This adds latency and synchronization overhead. `MoveCondPredicateToCpuPass` moves non-persistent buffer predicates to CPU at export time, eliminating per-inference D2H transfers. The predicate is typically a small scalar (e.g., a boolean flag), so keeping it on CPU has negligible memory impact. - Add `MoveCondPredicateToCpuPass` in `backends/cuda/passes/` - Add unit tests covering: - GPU buffer predicates moved to CPU - CPU buffer predicates unchanged - Computed predicates unaffected - Multiple `torch.cond` calls - Cross-attention cache pattern - Persistent buffers (state_dict) not moved - Add Python tests to `unittest-cuda` CI job in `cuda.yml` ghstack-source-id: ff22758 ghstack-comment-id: 3687889864 Pull-Request: #16378
meta-cla
bot
added
the
CLA Signed
larryliu0820
added a commit
that referenced
this pull request
Dec 23, 2025
Avoid device-to-host memory copies when evaluating `torch.cond` predicates. When a GPU buffer (e.g., a KV cache `initialized` flag) is used as a predicate for `torch.cond`, the runtime must synchronize and copy the predicate value from GPU to CPU on every forward pass to evaluate the condition. This adds latency and synchronization overhead. `MoveCondPredicateToCpuPass` moves non-persistent buffer predicates to CPU at export time, eliminating per-inference D2H transfers. The predicate is typically a small scalar (e.g., a boolean flag), so keeping it on CPU has negligible memory impact. - Add `MoveCondPredicateToCpuPass` in `backends/cuda/passes/` - Add unit tests covering: - GPU buffer predicates moved to CPU - CPU buffer predicates unchanged - Computed predicates unaffected - Multiple `torch.cond` calls - Cross-attention cache pattern - Persistent buffers (state_dict) not moved - Add Python tests to `unittest-cuda` CI job in `cuda.yml` ghstack-source-id: 8d724ef ghstack-comment-id: 3687889864 Pull-Request: #16378
larryliu0820
added a commit
that referenced
this pull request
Dec 24, 2025
Avoid device-to-host memory copies when evaluating `torch.cond` predicates. When a GPU buffer (e.g., a KV cache `initialized` flag) is used as a predicate for `torch.cond`, the runtime must synchronize and copy the predicate value from GPU to CPU on every forward pass to evaluate the condition. This adds latency and synchronization overhead. `MoveCondPredicateToCpuPass` moves non-persistent buffer predicates to CPU at export time, eliminating per-inference D2H transfers. The predicate is typically a small scalar (e.g., a boolean flag), so keeping it on CPU has negligible memory impact. - Add `MoveCondPredicateToCpuPass` in `backends/cuda/passes/` - Add unit tests covering: - GPU buffer predicates moved to CPU - CPU buffer predicates unchanged - Computed predicates unaffected - Multiple `torch.cond` calls - Cross-attention cache pattern - Persistent buffers (state_dict) not moved - Add Python tests to `unittest-cuda` CI job in `cuda.yml` ghstack-source-id: 4714546 ghstack-comment-id: 3687889864 Pull-Request: #16378
larryliu0820
added a commit
that referenced
this pull request
Dec 24, 2025
Avoid device-to-host memory copies when evaluating `torch.cond` predicates. When a GPU buffer (e.g., a KV cache `initialized` flag) is used as a predicate for `torch.cond`, the runtime must synchronize and copy the predicate value from GPU to CPU on every forward pass to evaluate the condition. This adds latency and synchronization overhead. `MoveCondPredicateToCpuPass` moves non-persistent buffer predicates to CPU at export time, eliminating per-inference D2H transfers. The predicate is typically a small scalar (e.g., a boolean flag), so keeping it on CPU has negligible memory impact. - Add `MoveCondPredicateToCpuPass` in `backends/cuda/passes/` - Add unit tests covering: - GPU buffer predicates moved to CPU - CPU buffer predicates unchanged - Computed predicates unaffected - Multiple `torch.cond` calls - Cross-attention cache pattern - Persistent buffers (state_dict) not moved - Add Python tests to `unittest-cuda` CI job in `cuda.yml` ghstack-source-id: d813c68 ghstack-comment-id: 3687889864 Pull-Request: #16378
larryliu0820
added a commit
that referenced
this pull request
Dec 24, 2025
Avoid device-to-host memory copies when evaluating `torch.cond` predicates. When a GPU buffer (e.g., a KV cache `initialized` flag) is used as a predicate for `torch.cond`, the runtime must synchronize and copy the predicate value from GPU to CPU on every forward pass to evaluate the condition. This adds latency and synchronization overhead. `MoveCondPredicateToCpuPass` moves non-persistent buffer predicates to CPU at export time, eliminating per-inference D2H transfers. The predicate is typically a small scalar (e.g., a boolean flag), so keeping it on CPU has negligible memory impact. - Add `MoveCondPredicateToCpuPass` in `backends/cuda/passes/` - Add unit tests covering: - GPU buffer predicates moved to CPU - CPU buffer predicates unchanged - Computed predicates unaffected - Multiple `torch.cond` calls - Cross-attention cache pattern - Persistent buffers (state_dict) not moved - Add Python tests to `unittest-cuda` CI job in `cuda.yml` ghstack-source-id: efe08be ghstack-comment-id: 3687889864 Pull-Request: #16378
larryliu0820
added a commit
that referenced
this pull request
Dec 24, 2025
Avoid device-to-host memory copies when evaluating `torch.cond` predicates. When a GPU buffer (e.g., a KV cache `initialized` flag) is used as a predicate for `torch.cond`, the runtime must synchronize and copy the predicate value from GPU to CPU on every forward pass to evaluate the condition. This adds latency and synchronization overhead. `MoveCondPredicateToCpuPass` moves non-persistent buffer predicates to CPU at export time, eliminating per-inference D2H transfers. The predicate is typically a small scalar (e.g., a boolean flag), so keeping it on CPU has negligible memory impact. - Add `MoveCondPredicateToCpuPass` in `backends/cuda/passes/` - Add unit tests covering: - GPU buffer predicates moved to CPU - CPU buffer predicates unchanged - Computed predicates unaffected - Multiple `torch.cond` calls - Cross-attention cache pattern - Persistent buffers (state_dict) not moved - Add Python tests to `unittest-cuda` CI job in `cuda.yml` ghstack-source-id: 58e9268 ghstack-comment-id: 3687889864 Pull-Request: #16378
larryliu0820
added a commit
that referenced
this pull request
Dec 25, 2025
Avoid device-to-host memory copies when evaluating `torch.cond` predicates. When a GPU buffer (e.g., a KV cache `initialized` flag) is used as a predicate for `torch.cond`, the runtime must synchronize and copy the predicate value from GPU to CPU on every forward pass to evaluate the condition. This adds latency and synchronization overhead. `MoveCondPredicateToCpuPass` moves non-persistent buffer predicates to CPU at export time, eliminating per-inference D2H transfers. The predicate is typically a small scalar (e.g., a boolean flag), so keeping it on CPU has negligible memory impact. - Add `MoveCondPredicateToCpuPass` in `backends/cuda/passes/` - Add unit tests covering: - GPU buffer predicates moved to CPU - CPU buffer predicates unchanged - Computed predicates unaffected - Multiple `torch.cond` calls - Cross-attention cache pattern - Persistent buffers (state_dict) not moved - Add Python tests to `unittest-cuda` CI job in `cuda.yml` ghstack-source-id: b439eb3 ghstack-comment-id: 3687889864 Pull-Request: #16378
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.
Avoid device-to-host memory copies when evaluating
torch.condpredicates.When a GPU buffer (e.g., a KV cache
initializedflag) is used as a predicate fortorch.cond, the runtime must synchronize and copy the predicate value from GPU to CPU on every forward pass to evaluate the condition. This adds latency and synchronization overhead.MoveCondPredicateToCpuPassmoves non-persistent buffer predicates to CPU at export time, eliminating per-inference D2H transfers. The predicate is typically a small scalar (e.g., a boolean flag), so keeping it on CPU has negligible memory impact.MoveCondPredicateToCpuPassinbackends/cuda/passes/torch.condcallsunittest-cudaCI job incuda.yml