ggml-cuda: reuse cached experts during overflow staging - #44
Draft
GenerelSchwerz wants to merge 1 commit into
Draft
ggml-cuda: reuse cached experts during overflow staging#44GenerelSchwerz wants to merge 1 commit into
GenerelSchwerz wants to merge 1 commit into
Conversation
Assisted-by: Codex
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stacked on #42. Reuse resident expert-cache slabs when an MoE operation exceeds cache capacity, while staging nonresident slabs from host memory. Add stream ordering and focused mixed D2D/H2D regression coverage. Validation: exact 8K/32K tokens and matched-parent PPL; cache48 prefill +2.15% at 8K and +1.95% at 32K with equal VRAM; Compute Sanitizer reports zero errors.