[Unified Cache][1/N]: Support cache contract for external linker - #37091
Merged
hzh0425 merged 2 commits intoAug 30, 2026
Merged
Conversation
hzh0425
requested review from
Ying1123,
alphabetc1,
hanming-lu,
hnyls2002,
huangtingwei9988,
ispobock,
merrymercy,
xiezhq-hermann and
yizhang2077
as code owners
August 30, 2026 06:16
Collaborator
Author
|
/rerun-test test/registered/unit/mem_cache/test_unified_radix_cache_unittest.py |
Collaborator
Author
|
/rerun-group radix_cache/unified_radix_tree |
Contributor
|
Results for 🚀 |
Contributor
|
Results for 🚀 🚀 🚀 🚀 🚀 |
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
hzh0425
force-pushed
the
external-linker-cache-contract
branch
from
August 30, 2026 06:23
ee17743 to
01636dc
Compare
huangtingwei9988
approved these changes
Aug 30, 2026
Collaborator
Author
5 tasks
saturn-acc
pushed a commit
to saturn-acc/sglang
that referenced
this pull request
Aug 31, 2026
…-project#37091) Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
nzr-niu
pushed a commit
to nzr-niu/sglang
that referenced
this pull request
Sep 1, 2026
…-project#37091) Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
RolaoDenthu
pushed a commit
to RolaoDenthu/sglang
that referenced
this pull request
Sep 1, 2026
…-project#37091) Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
This was referenced Sep 1, 2026
This was referenced Sep 1, 2026
EdwardXuy
added a commit
to EdwardXuy/sglang-Ascend
that referenced
this pull request
Sep 1, 2026
DeepSeek-V4 needs --tp-size 16/--dp-size 16, so the 2-card linux-aarch64-a3-2 runner cannot host it; switch to linux-aarch64-a3-16. Replace the two 20260828 images with main-cann9.0.0-a3 (daily build, contains sgl-project#37091 -> expected RED) plus the 20260828-cann9.0.0-a3 snapshot (control -> expected GREEN).
EdwardXuy
added a commit
to EdwardXuy/sglang-Ascend
that referenced
this pull request
Sep 1, 2026
The bundled image sglang cannot reproduce sgl-project#37091: the main image crashes at cuda-graph capture (aclnnHcPre missing in libopapi.so) and the 8/28 image predates the PR. Checkout upstream sglang main and override via PYTHONPATH so the recover_after_unevict result-param change is exercised, while overlaying the ascend test utils from this PR's checkout.
EdwardXuy
added a commit
to EdwardXuy/sglang-Ascend
that referenced
this pull request
Sep 2, 2026
Both cann9.0.0 images fail at capture_decode_graph with 'aclnnHcPre not in libopapi.so': the DSV4 mHC pre-norm path calls torch.ops.custom.npu_hc_pre, which cann9.0.0 does not ship. Use the 20260828 cann9.1.0 snapshot (has HcPre) and keep the PYTHONPATH override to upstream main (contains sgl-project#37091).
5 tasks
Merged
5 tasks
StevenChenSE
pushed a commit
to StevenChenSE/sglang
that referenced
this pull request
Sep 6, 2026
…-project#37091) Co-authored-by: 晟海 <huangtingwei.htw@antgroup.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
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.
Summary
This is the first PR in the external linker series.
This PR is split from the original full PR: #35687
This PR only introduces the cache-side contracts. Linker wiring and backends will follow in subsequent PRs.
Test Plan
pre-commit run --from-ref HEAD^ --to-ref HEADCI States
Latest PR Test (Base): ✅ Run #33297464622
Latest PR Test (Extra): ✅ Run #33297464442
Latest PR Test (AMD ROCm 7.2): ❌ Run #33297464616