Add native DeepSeek-V4 hybrid attention orchestration - #6402
Draft
FDecaYed wants to merge 9 commits into
Draft
Conversation
Signed-off-by: Deyu Fu <deyuf@nvidia.com>
(cherry picked from commit b7c36fa) Signed-off-by: Hongxiao Bai <hongxiaob@nvidia.com> Signed-off-by: Deyu Fu <deyuf@nvidia.com>
Signed-off-by: Deyu Fu <deyuf@nvidia.com>
Signed-off-by: Deyu Fu <deyuf@nvidia.com>
Signed-off-by: Deyu Fu <deyuf@nvidia.com>
Signed-off-by: Deyu Fu <deyuf@nvidia.com>
Signed-off-by: Deyu Fu <deyuf@nvidia.com>
Signed-off-by: Deyu Fu <deyuf@nvidia.com>
Signed-off-by: Deyu Fu <deyuf@nvidia.com>
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
This was referenced Aug 10, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add native DeepSeek-V4 hybrid attention orchestration
Summary
Wire the D1 SBHD CSA primitives into native DeepSeek-V4 attention orchestration, module specs, grouped output, MTP propagation, and indexer-loss scheduling/logging.
Scope
DSv4HybridAttentionandDSv4HybridSelfAttentionSBHD construction and execution.models/gptfilename is a shared experimental-attention factory and does not add GPTModel construction support.ProcessGroupCollectioninputs for cross-pipeline logging behavior.dsa_kernel_backend='none'for this native slice; D3 adds the fused backend.AbsorbedMLAintegration on the current-main implementation instead of replacing it with a dev copy.Non-goals
Review boundary and dependencies
Requires #6400 (D1) and P6/#5944. The local branch currently carries the complete D1 prerequisite line through
c463cbed9919; this will still be an independent PR targetingmain.0ecb394a67d2ae2b89c20d8d489c48fa5b5b1ef9c463cbed9919bcc662fd5b4282546367f1852c32Please review the own commit only. After D1 and #5944 merge, it will be replayed directly onto then-current
main.Provenance
Reconstructed from current main plus the post-#6020 DSv4 residual, using #5795 only as behavior/test evidence. It follows the current post-#6372 CSA namespace and preserves the teacher semantics established by #5960.
Validation
Passed locally:
Signed-off-bytrailer;git diff --check;Runtime pytest is unavailable in the bare macOS environment because PyTorch/CUDA is not installed. Focused CUDA tests and full functional CI remain required after publication.
Local artifact
D2-native-dsv4-attention-orchestration.patch, generated from the own commit only. Verify it against SHA256SUMS.
Before publication
After D1 and #5944 merge, replay only D2’s own commit onto current
main, re-audit any intervening ordinary-DSA andAbsorbedMLAchanges, then rerun focused/static validation and full functional CI.