Hyena support for flash decode API #14315
Merged
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
…gatron Signed-off-by: John St John <jstjohn@nvidia.com>
…odel Signed-off-by: John St John <jstjohn@nvidia.com>
…te-forward-inf Signed-off-by: John St John <jstjohn@nvidia.com>
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
Signed-off-by: John St John <jstjohn@nvidia.com>
Signed-off-by: John St John <jstjohn@nvidia.com>
|
[🤖]: Hi @jstjohn 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully. So it might be time to merge this PR or get some approvals. |
…he config Signed-off-by: John St John <jstjohn@nvidia.com>
Signed-off-by: John St John <jstjohn@nvidia.com>
JRD971000
approved these changes
Jul 29, 2025
jstjohn
added a commit
to NVIDIA/bionemo-framework
that referenced
this pull request
Jul 29, 2025
…tween inputs/embeddings, will be merged to nemo in NVIDIA-NeMo/NeMo#14315 Signed-off-by: John St John <jstjohn@nvidia.com>
|
[🤖]: Hi @jstjohn 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully. So it might be time to merge this PR or get some approvals. |
github-merge-queue bot
pushed a commit
to NVIDIA/bionemo-framework
that referenced
this pull request
Jul 31, 2025
### Description - Support for Flash Decode - Do not yet support cudagraph. Depends on NeMo PR: NVIDIA-NeMo/NeMo#14315 --------- Signed-off-by: John St John <jstjohn@nvidia.com>
nasretdinovr
pushed a commit
to nasretdinovr/NeMo
that referenced
this pull request
Aug 8, 2025
* Adding updates to hyena forward pass that reflect newer changes to megatron Signed-off-by: John St John <jstjohn@nvidia.com> * Make it so recompute num layers do not need to be a multiple of the model Signed-off-by: John St John <jstjohn@nvidia.com> * Update formatting and change grad context for inference time Signed-off-by: John St John <jstjohn@nvidia.com> * Address pylint error Signed-off-by: John St John <jstjohn@nvidia.com> * Add ability to set the embedding/output weight sharing setting from the config Signed-off-by: John St John <jstjohn@nvidia.com> --------- Signed-off-by: John St John <jstjohn@nvidia.com>
guyueh1
pushed a commit
to guyueh1/NeMo
that referenced
this pull request
Aug 25, 2025
* Adding updates to hyena forward pass that reflect newer changes to megatron Signed-off-by: John St John <jstjohn@nvidia.com> * Make it so recompute num layers do not need to be a multiple of the model Signed-off-by: John St John <jstjohn@nvidia.com> * Update formatting and change grad context for inference time Signed-off-by: John St John <jstjohn@nvidia.com> * Address pylint error Signed-off-by: John St John <jstjohn@nvidia.com> * Add ability to set the embedding/output weight sharing setting from the config Signed-off-by: John St John <jstjohn@nvidia.com> --------- Signed-off-by: John St John <jstjohn@nvidia.com> Signed-off-by: Guyue Huang <guyueh@nvidia.com>
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.
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information