[Executorch] Add non-flash SDPA for decode#18648
Closed
kimishpatel wants to merge 19 commits into
Closed
Conversation
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18648
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 2 Cancelled Jobs, 8 Unrelated FailuresAs of commit 126e8bb with merge base 1debeb6 ( NEW FAILURE - The following job has failed:
CANCELLED JOBS - The following jobs were cancelled. Please retry:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
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. |
This was referenced Apr 1, 2026
meta-cla
Bot
added
the
CLA Signed
This PR needs a
|
digantdesai
approved these changes
Apr 1, 2026
digantdesai
left a comment
digantdesai
left a comment
Contributor
There was a problem hiding this comment.
Review automatically exported from Phabricator review in Meta.
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
This was referenced Apr 6, 2026
Closed
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
Add cpu_sdpa template function in op_sdpa_impl.h that provides a simpler SDPA implementation using standard GEMM (no tiling). This is useful as a baseline and for cases where flash attention is not optimal. The implementation uses a single SeqDim parameter for all tensors and supports causal masking, attention masks, GQA, and multi-threading. During decode (seq_len == 1), the tiled flash attention implementation has unnecessary overhead from its blocking/tiling logic. The simpler unfused SDPA path using direct GEMM is more efficient for single-query attention, yielding ~25-30% decode throughput improvement on S25 (41 -> 53 tok/s for 1.4B parameter model). This makes cpu_sdpa always available (previously gated behind ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and inputs are not quantized. Prefill continues to use flash attention. Differential Revision: [D96044318](https://our.internmc.facebook.com/intern/diff/D96044318/) [ghstack-poisoned]
|
Hi @kimishpatel! Thank you for your pull request. We require contributors to sign our Contributor License Agreement, and yours needs attention. You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
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.
Stack from ghstack (oldest at bottom):
Add cpu_sdpa template function in op_sdpa_impl.h that provides a
simpler SDPA implementation using standard GEMM (no tiling). This is
useful as a baseline and for cases where flash attention is not optimal.
The implementation uses a single SeqDim parameter for all tensors and
supports causal masking, attention masks, GQA, and multi-threading.
During decode (seq_len == 1), the tiled flash attention implementation
has unnecessary overhead from its blocking/tiling logic. The simpler
unfused SDPA path using direct GEMM is more efficient for single-query
attention, yielding ~25-30% decode throughput improvement on S25
(41 -> 53 tok/s for 1.4B parameter model).
This makes cpu_sdpa always available (previously gated behind
ET_USE_UNFUSED_SDPA) and dispatches to it when seq_len == 1 and
inputs are not quantized. Prefill continues to use flash attention.
Differential Revision: D96044318