perf(cuda): fuse Laguna MoE expert paths#23
Draft
davide221 wants to merge 4 commits into
Draft
Conversation
Keep the CUDA-only fused MoE op explicit in the CPU dispatcher so non-CUDA builds do not fail on missing switch coverage. Co-authored-by: Codex <codex@openai.com>
Bump the RPC protocol patch guard after the op-count change, include TQ3_0 in the unsupported CPU clamp cases, and avoid unreachable breaks after noreturn CPU-only guards. Co-authored-by: Codex <codex@openai.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Draft companion PR for the Laguna hub performance branch.
Summary:
Validation:
This is draft/WIP so we can preserve the branch while continuing byte-identical checks and the next decode-speed pass.