[PR #1386] [MERGED] [CI]Add testcase test_disaggregation_different_tp and fix potential network issues

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#2210

bsakaguchi commented

2026-10-29 21:33:42 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/kvcache-ai/Mooncake/pull/1386
Author: @luketong777
Created: 1/15/2026
Status: ✅ Merged
Merged: 1/16/2026
Merged by: @stmatengss

Base: main ← Head: add-different-tp-testcase

📝 Commits (7)

225a27b feat: Support automatic selection of ERDMA repository based on Ubuntu version - compatible with Ubuntu 22.04 (jammy) and Ubuntu 24.04 (noble)
4c47f2b fix: mount test dataset and enhance test output for hicache_storage_mooncake_backend
0f5ac0a feat: Add retry mechanism with incremental delays for GitHub artifact download in get_whl function
f66c26e fix: use predefined SHA variable instead of github.sha in T-One job name for consistency
2a9b4da add ci test case: test_disaggregation_different_tp
4cdca5d add return in test_disaggregation_different_tp
6046c8a fix (get_whl): Move GIT_REPO and ARTIFACT_ID validation outside retry loop for efficiency

📊 Changes

4 files changed (+217 additions, -10 deletions)

View changed files

📝 .github/workflows/integration-test.yml (+1 -1)
📝 scripts/tone_tests/scripts/common.sh (+57 -8)
➕ scripts/tone_tests/scripts/test_disaggregation_different_tp.sh (+158 -0)
📝 scripts/tone_tests/scripts/test_hicache_storage_mooncake_backend.sh (+1 -1)

📄 Description

Description

Add new CI testcase test_disaggregation_different_tp
Implement retry mechanism with incremental delays for GitHub artifact downloads to handle network instability
Mount test dataset locally to avoid network fluctuations during data download and add verbose output for hicache_storage_mooncake_backend test debugging
Support automatic ERDMA repository selection for Ubuntu 22.04 and 24.04
Fix T-One job naming consistency by using predefined SHA variable

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?

I manually triggered the T-One job to run tests

Checklist

I have performed a self-review of my own code.
I have formatted my own code using ./scripts/code_format.sh before submitting.
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/1386 **Author:** [@luketong777](https://github.com/luketong777) **Created:** 1/15/2026 **Status:** ✅ Merged **Merged:** 1/16/2026 **Merged by:** [@stmatengss](https://github.com/stmatengss) **Base:** `main` ← **Head:** `add-different-tp-testcase` --- ### 📝 Commits (7) - [`225a27b`](https://github.com/kvcache-ai/Mooncake/commit/225a27b2e8a6f5cd91cad47e7100792189027167) feat: Support automatic selection of ERDMA repository based on Ubuntu version - compatible with Ubuntu 22.04 (jammy) and Ubuntu 24.04 (noble) - [`4c47f2b`](https://github.com/kvcache-ai/Mooncake/commit/4c47f2b3bfff554e25bb4c4393526e9794a1726b) fix: mount test dataset and enhance test output for hicache_storage_mooncake_backend - [`0f5ac0a`](https://github.com/kvcache-ai/Mooncake/commit/0f5ac0a00358024fb731ee09d26a6e4f6ea24816) feat: Add retry mechanism with incremental delays for GitHub artifact download in get_whl function - [`f66c26e`](https://github.com/kvcache-ai/Mooncake/commit/f66c26e43fb566bf624b35a8647cf493145250ca) fix: use predefined SHA variable instead of github.sha in T-One job name for consistency - [`2a9b4da`](https://github.com/kvcache-ai/Mooncake/commit/2a9b4dae077674f86515fbb7fa9361e7de655197) add ci test case: test_disaggregation_different_tp - [`4cdca5d`](https://github.com/kvcache-ai/Mooncake/commit/4cdca5d78b70e0119ff801e19a7b732eff9d546a) add return in test_disaggregation_different_tp - [`6046c8a`](https://github.com/kvcache-ai/Mooncake/commit/6046c8a22ece46c77be6a825da854950383dc407) fix (get_whl): Move GIT_REPO and ARTIFACT_ID validation outside retry loop for efficiency ### 📊 Changes **4 files changed** (+217 additions, -10 deletions) <details> <summary>View changed files</summary> 📝 `.github/workflows/integration-test.yml` (+1 -1) 📝 `scripts/tone_tests/scripts/common.sh` (+57 -8) ➕ `scripts/tone_tests/scripts/test_disaggregation_different_tp.sh` (+158 -0) 📝 `scripts/tone_tests/scripts/test_hicache_storage_mooncake_backend.sh` (+1 -1) </details> ### 📄 Description ## Description  - Add new CI testcase test_disaggregation_different_tp - Implement retry mechanism with incremental delays for GitHub artifact downloads to handle network instability - Mount test dataset locally to avoid network fluctuations during data download and add verbose output for hicache_storage_mooncake_backend test debugging - Support automatic ERDMA repository selection for Ubuntu 22.04 and 24.04 - Fix T-One job naming consistency by using predefined SHA variable ## Type of Change * Types - [ ] Bug fix - [ ] New feature - [ ] Transfer Engine - [ ] Mooncake Store - [ ] Mooncake EP - [ ] Integration - [ ] P2P Store - [ ] Python Wheel - [ ] Breaking change - [x] CI/CD - [ ] Documentation update - [ ] Other ## How Has This Been Tested?  I manually triggered the T-One job to run tests ## Checklist - [ ] I have performed a self-review of my own code. - [ ] I have formatted my own code using `./scripts/code_format.sh` before submitting. - [ ] I have updated the documentation. - [ ] 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 #1386] [MERGED] [CI]Add testcase test_disaggregation_different_tp and fix potential network issues #2210