[PR #1222] [MERGED] [EP] Fix the tensorSize of the barrier op

No labels

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

kvcache-ai/Mooncake#2087

bsakaguchi commented

2026-10-29 21:32:41 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/kvcache-ai/Mooncake/pull/1222
Author: @UNIDY2002
Created: 12/17/2025
Status: ✅ Merged
Merged: 12/17/2025
Merged by: @stmatengss

Base: main ← Head: sunxun/barrier-fix

📝 Commits (2)

be0b0fd Fix the tensorSize of the barrier op
038cd32 Fix

📊 Changes

2 files changed (+12 additions, -2 deletions)

View changed files

📝 mooncake-ep/src/mooncake_backend.cpp (+5 -2)
📝 mooncake-wheel/tests/test_mooncake_backend_cpu.py (+7 -0)

📄 Description

Description

Previously, the tensorSize of the barrier op was set to 0, causing the entire collective communication to be skipped.

This PR changes the tensorSize to 1.

Type of Change

Types
- Bug fix
- New feature
  - Transfer Engine
  - Mooncake Store
  - Mooncake EP
  - Integration
  - P2P Store
  - Python Wheel
- Breaking change
- CI/CD
- Documentation update
- Other

How Has This Been Tested?

SGLang end-to-end test passes.

Checklist

I have performed a self-review of my own code.
I have updated the documentation.
I have added tests to prove my changes are effective.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/kvcache-ai/Mooncake/pull/1222 **Author:** [@UNIDY2002](https://github.com/UNIDY2002) **Created:** 12/17/2025 **Status:** ✅ Merged **Merged:** 12/17/2025 **Merged by:** [@stmatengss](https://github.com/stmatengss) **Base:** `main` ← **Head:** `sunxun/barrier-fix` --- ### 📝 Commits (2) - [`be0b0fd`](https://github.com/kvcache-ai/Mooncake/commit/be0b0fdc6f0ed63427b6fa0dfc68f4e7f4e4f943) Fix the tensorSize of the barrier op - [`038cd32`](https://github.com/kvcache-ai/Mooncake/commit/038cd3235716356cbe561c4b08b7a73412602cf0) Fix ### 📊 Changes **2 files changed** (+12 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `mooncake-ep/src/mooncake_backend.cpp` (+5 -2) 📝 `mooncake-wheel/tests/test_mooncake_backend_cpu.py` (+7 -0) </details> ### 📄 Description ## Description  Previously, the tensorSize of the barrier op was set to 0, causing the entire collective communication to be skipped. This PR changes the tensorSize to 1. ## Type of Change * Types - [x] Bug fix - [ ] New feature - [ ] Transfer Engine - [ ] Mooncake Store - [ ] Mooncake EP - [ ] Integration - [ ] P2P Store - [ ] Python Wheel - [ ] Breaking change - [ ] CI/CD - [ ] Documentation update - [ ] Other ## How Has This Been Tested?  SGLang end-to-end test passes. ## Checklist - [x] I have performed a self-review of my own code. - [ ] I have updated the documentation. - [x] I have added tests to prove my changes are effective. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

closed this issue
added the
pull-request
label

Rows
Columns

[PR #1222] [MERGED] [EP] Fix the tensorSize of the barrier op #2087