Skip to content

[BugFix]: Fix HiMamba HiCache prefetch hang after L3 sidecar transfer #27366

Merged
ispobock merged 1 commit into
sgl-project:mainfrom
hzh0425:fix/mamba-ci-origin-main
Jun 5, 2026
Merged

[BugFix]: Fix HiMamba HiCache prefetch hang after L3 sidecar transfer #27366
ispobock merged 1 commit into
sgl-project:mainfrom
hzh0425:fix/mamba-ci-origin-main

Conversation

@hzh0425

@hzh0425 hzh0425 commented Jun 5, 2026

Copy link
Copy Markdown
Collaborator

Motivation

Fix qwen3.5 hicache hanging: https://github.com/sgl-project/sglang/actions/runs/26985767961/job/79634930991

Modifications

Accuracy Tests

Speed Tests and Profiling

Checklist

Review and Merge Process

  1. Ping Merge Oncalls to start the process. See the PR Merge Process.
  2. Get approvals from CODEOWNERS and other reviewers.
  3. Trigger CI tests with comments or contact authorized users to do so.
    • Common commands include /tag-and-rerun-ci, /tag-run-ci-label, /rerun-failed-ci
  4. After green CI and required approvals, ask Merge Oncalls or people with Write permission to merge the PR.

CI States

Latest PR Test (Base): ⏳ Run #27005095367
Latest PR Test (Extra): ❌ Run #27005095201

@hzh0425

hzh0425 commented Jun 5, 2026

Copy link
Copy Markdown
Collaborator Author

/rerun-test test/registered/hicache/test_qwen35_hicache.py

@github-actions

github-actions Bot commented Jun 5, 2026

Copy link
Copy Markdown
Contributor

Results for /rerun-test test/registered/hicache/test_qwen35_hicache.py:

🚀 4-gpu-h100 (1 test): ✅ View workflow run

cd test/ && python3 registered/hicache/test_qwen35_hicache.py

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request modifies the can_terminate_prefetch method in hi_mamba_radix_cache.py to ensure that prefetch operations do not terminate if pool transfers are still ongoing. There are no review comments, and I have no feedback to provide.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

@ispobock

ispobock commented Jun 5, 2026

Copy link
Copy Markdown
Collaborator

@ispobock

ispobock commented Jun 5, 2026

Copy link
Copy Markdown
Collaborator

/tag-and-rerun-ci

@github-actions github-actions Bot added the run-ci label Jun 5, 2026
@ispobock

ispobock commented Jun 5, 2026

Copy link
Copy Markdown
Collaborator

/rerun-group radix_cache/unified_radix_tree

@github-actions

github-actions Bot commented Jun 5, 2026

Copy link
Copy Markdown
Contributor

Results for /rerun-group radix_cache/unified_radix_tree:

🚀 4-gpu-h100 (3 tests): ✅ View workflow run

cd test/ && python3 registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_cp.py
cd test/ && python3 registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_dsv4.py
cd test/ && python3 registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_mamba.py

🚀 2-gpu-h100 (2 tests): ✅ View workflow run

cd test/ && python3 registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_full.py
cd test/ && python3 registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_swa.py

🚀 8-gpu-h200 (1 test): ✅ View workflow run

cd test/ && python3 registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_nightly.py

@ispobock

ispobock commented Jun 5, 2026

Copy link
Copy Markdown
Collaborator

/rerun-group hicache

@github-actions

github-actions Bot commented Jun 5, 2026

Copy link
Copy Markdown
Contributor

Results for /rerun-group hicache:

🚀 1-gpu-h100 (2 tests): ✅ View workflow run

cd test/ && python3 registered/hicache/test_hicache_spec_file_storage.py
cd test/ && python3 registered/hicache/test_hicache_variants.py

🚀 2-gpu-h100 (5 tests): ❌ View workflow run

cd test/ && python3 registered/hicache/test_hicache_spec_mooncake_storage.py
cd test/ && python3 registered/hicache/test_hicache_storage_3fs_backend.py
cd test/ && python3 registered/hicache/test_hicache_storage_file_backend.py
cd test/ && python3 registered/hicache/test_hicache_storage_mooncake_backend.py
cd test/ && python3 registered/hicache/test_hicache_storage_runtime_attach_detach.py

🚀 1-gpu-5090 (1 test): ✅ View workflow run

cd test/ && python3 registered/hicache/test_hicache_storage.py

🚀 4-gpu-h100 (1 test): ✅ View workflow run

cd test/ && python3 registered/hicache/test_qwen35_hicache.py

@ispobock

ispobock commented Jun 5, 2026

Copy link
Copy Markdown
Collaborator

3fs issue still in investigation: https://github.com/sgl-project/sglang/actions/runs/27007422761

@ispobock ispobock merged commit faa6286 into sgl-project:main Jun 5, 2026
191 of 225 checks passed
monkeyLoveding pushed a commit to monkeyLoveding/sglang_open that referenced this pull request Jun 9, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants