mirror of
https://github.com/deepseek-ai/DeepEP.git
synced 2026-11-05 00:47:32 +00:00
[PR #79] [MERGED] Support zero-copy for low-latency combine #430
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepEP#430
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
📋 Pull Request Information
Original PR: https://github.com/deepseek-ai/DeepEP/pull/79
Author: @LyricZhao
Created: 3/18/2025
Status: ✅ Merged
Merged: 3/18/2025
Merged by: @LyricZhao
Base:
main← Head:zero-copy-combine📝 Commits (2)
dcaf73eSupport zero-copy for low-latency combine6646547Support zero-copy for low-latency combine📊 Changes
7 files changed (+80 additions, -28 deletions)
View changed files
📝
csrc/config.hpp(+6 -1)📝
csrc/deep_ep.cpp(+20 -3)📝
csrc/deep_ep.hpp(+5 -1)📝
csrc/kernels/api.cuh(+2 -1)📝
csrc/kernels/internode_ll.cu(+6 -4)📝
deep_ep/buffer.py(+22 -5)📝
tests/test_low_latency.py(+19 -13)📄 Description
No description provided
🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.
QP_DEPTHfor low latency kernels. #561