[CI] Add /run-full-ci and /run-extra-ci slash commands - #38734
Merged
Merged
Conversation
Extra CI could only be triggered as a side effect of `/tag-and-rerun-ci extra`, and there was no way to run the extra tier alone — a baseline-green PR had to re-sweep baseline to get extra. /run-full-ci runs baseline + extra (short form of `/tag-and-rerun-ci extra`, sharing its code path). /run-extra-ci applies both labels and reruns only `PR Test Extra`, leaving baseline runs alone. The /rerun-* spellings are accepted as aliases. Existing commands are unchanged. Both reuse can_tag_run_ci_label + can_rerun_failed_ci, so every user already in CI_PERMISSIONS.json gets them with no roster change. Also fixes the /rerun-group doc example, which referenced a `hicache` group that doesn't exist.
alisonshao
requested review from
Fridge003,
HaiShaw,
JustinTong0323,
Kangyan-Zhou,
bingxche,
ispobock,
merrymercy,
sogalin,
wisclmy0611 and
zijiexia
as code owners
September 9, 2026 20:40
github-actions
Bot
added
the
documentation
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Automations to automatically generate PRs for you. |
Collaborator
Author
|
/run-extra-ci |
Collaborator
Author
|
/tag-and-rerun-ci extra |
pllimax
added a commit
to pllimax/sglang
that referenced
this pull request
Sep 10, 2026
* origin/main: (27 commits) [Simulator] Give the OFFLINE/BLOCKING comparison tolerances real headroom (sgl-project#38732) [Config] msgspec.Struct for the config tier (sgl-project#38753) [AMD] ci: move the miles nightlies from rocm700 to rocm10 (sgl-project#37495) [Config] One writer for the declaration stash; no exception to the write seal (sgl-project#38752) docker(xpu): drop redundant setvars.sh from torch_memory_saver RUN (sgl-project#38665) [XPU][Fix] Pack device-pointer tables as uint64 to avoid 64-bit address overflow (sgl-project#35051) [CI] Temporarily disable GB300 tests (sgl-project#38770) [diffusion] feat: spill large tensors over shared memory like numpy arrays (sgl-project#38656) [diffusion] refactor: refactor utility ownership and document helper placement (sgl-project#38699) [NPU]Support GLM5.2 and FP8 DSA&Indexer kvcache for 950 (sgl-project#38250) [CI] Answer unrecognized slash commands instead of skipping silently (sgl-project#38736) [AMD] Parallelize aiter spec-decode KV index building over token blocks (sgl-project#37659) [DSv4] Integrate TRT-LLM DSv4 Attention for SM100/103 (sgl-project#30805) Add Opt-In for GLM-5.3 Flash breakable prefill CUDA graphs (sgl-project#38522) [CI] Install helion 1.4.0 for the KDA Helion kernel tests (sgl-project#38688) [Rust] Gate health on startup warmup completion (sgl-project#37994) [HiCache] Replace skip_lock_node_ids with a segment lock protocol (sgl-project#36848) feat: add optimized Domino rollout to DFlash V2 (sgl-project#36899) [CI] Add /run-full-ci and /run-extra-ci slash commands (sgl-project#38734) [Model] Support GLM-5.3 Flash NVFP4 loading (sgl-project#38621) ...
mqhc2020
pushed a commit
to mqhc2020/sglang
that referenced
this pull request
Sep 15, 2026
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
1 participant
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.
Extra CI could only be triggered as a side effect of
/tag-and-rerun-ci extra, and there was no way to run the extra tier alone — a baseline-green PR had to re-sweep baseline just to get extra./run-full-ci— baseline + extra. Short form of/tag-and-rerun-ci extra, sharing its code path./run-extra-ci— applies both labels, reruns onlyPR Test Extra, leaving baseline runs alone./rerun-full-ciand/rerun-extra-ciare accepted as aliases. Existing commands are unchanged.Both reuse
can_tag_run_ci_label+can_rerun_failed_cirather than adding a permission key, so every user already inCI_PERMISSIONS.jsongets them with no roster change./run-extra-ciis rerun-only —pr-test-extra.yml's dispatch inputs carry nopr_head_sha, so dispatching a fork PR would testmaininstead of the PR. It reuses_latest_run_per_workflowso it can't spawn a duplicate that fights a live run for runners. No workflow is touched except the handler's allowlist.Docs updated, including fixing the
/rerun-groupexample — it referenced ahicachegroup that doesn't exist;rust-serveris the only registered group.CI States
Latest PR Test (Base): 🚫 Run #34402441856
Latest PR Test (Extra): 🚫 Run #34402441470
Latest PR Test (AMD ROCm 10): 🚫 Run #34402441758