feat: Reduce number of Cuda IPC in Refit#568
Closed
guyueh1 wants to merge 8 commits intoyifu/deepseek_ep_mainfrom
Closed
feat: Reduce number of Cuda IPC in Refit#568guyueh1 wants to merge 8 commits intoyifu/deepseek_ep_mainfrom
guyueh1 wants to merge 8 commits intoyifu/deepseek_ep_mainfrom
Conversation
Signed-off-by: Guyue Huang <guyueh@nvidia.com>
parthchadha
reviewed
Jun 26, 2025
|
|
||
| # pack tensors in gathered_hf_params to a big tensor | ||
| type_to_packed_big_tensor_size = defaultdict(lambda : 0) | ||
| key_to_type_and_offset_and_size_in_big_tensor = [] |
Contributor
There was a problem hiding this comment.
I would suggest running this code through cursor to simplify the code, var names, typos..
Contributor
Author
There was a problem hiding this comment.
yes this is so far a draft, i will do some cleanup
Signed-off-by: Guyue Huang <guyueh@nvidia.com>
Signed-off-by: Guyue Huang <guyueh@nvidia.com>
guyueh1
changed the title
Signed-off-by: Guyue Huang <guyueh@nvidia.com>
Contributor
Author
|
DO NOT merge, raised a new PR to main #589 |
…EFIT Signed-off-by: Guyue Huang <guyueh@nvidia.com>
Signed-off-by: Guyue Huang <guyueh@nvidia.com>
Contributor
Author
|
closing because #589 is merged |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do ?
Reduce number of cuda IPC in refit, packing parameters into big tensors and unpack in Vllm.
Issues
List issues that this PR closes (syntax):
Usage
# Add a code snippet demonstrating how to use thisBefore your PR is "Ready for review"
Pre checks:
Additional Information