Bump version to 0.2.0 - #730
Merged
Merged
Conversation
timethink
pushed a commit
to timethink/sglang
that referenced
this pull request
Mar 9, 2025
cen121212
pushed a commit
to cen121212/sglang
that referenced
this pull request
Nov 10, 2025
…lti-machine test cases. (sgl-project#730) * Update daily-build-test-npu-innersource.yml * Create mmmu-val.yaml * Update test_disaggregation_decode_tp.py * Update test_disaggregation_decode_dp.py * Update run_suite.py * Update test_qwen_models.py * Update test_disaggregation_prefill_pp.py * Update test_disaggregation_decode_tp.py * Update test_disaggregation_decode_dp.py * Update daily-build-test-npu-innersource.yml * Update pr-test-npu-debug.yml * Update daily-build-test-npu-innersource.yml
cherryblo
added a commit
to cherryblo/sglang-project
that referenced
this pull request
Jul 2, 2026
Update nightly-test-npu-e2e-multi-node.yml
efschu
pushed a commit
to efschu/htsglang
that referenced
this pull request
Aug 17, 2026
…ndle
THE SPECIMEN, 2026-08-17 14:48:22, on a boot whose warmup generation never
reached a first token:
arming tp_to_pp: decode bundle complete: 0 reqs decoded in 183.6 s
(13777 tok prefill waiting) -- exit condition: decode drained
The tp phase was entered with NOTHING decoding, sat 183.6 s (released by the
180 s decode-stall cap), and left claiming completion. Six such cycles in one
boot.
`bundle_at_phase_entry` is `running_bs` AT ENTRY (:2093), so 0 means the bundle
was never resident: there was no work to drain and the visit accomplished
nothing. The sentence was the defect -- a drained bundle and an empty visit
produced the SAME words, differing only by a number that reads as a quantity
rather than as a verdict, so a log scan showed "complete" either way.
LEAVING IS STILL CORRECT and is unchanged: a decode layout with nothing to
decode should yield to prefill. The direction stays TP_TO_PP in both cases;
only the diagnosis differs. This is a wording change in the sense that a wrong
instrument reading is a wording change.
WHY IT MATTERS BEYOND WORDING. The sgl-project#699 admission-wedge detector fired 17 times
on this same boot -- "1 queued, 0 running, and NO first token for 288.0s. Work
is admissible and nothing is serving it" -- and recorded "no phase-policy
corroboration seen". An empty decode phase standing beside a non-empty backlog
IS that corroboration: it is the layout's own evidence that work is queued which
nothing is making runnable. The vacuous message was withholding it, so the two
instruments could not be put together. The new line names ADMISSION as the
suspect and points at sgl-project#731 and at the sgl-project#699 line by number.
Also corrected: the healthy path said "{bundle} reqs decoded", but that number
is the count AT ENTRY, not the number decoded. It now says "{bundle} req bundle
drained", which is what it measures.
TESTS test/registered/unit/managers/test_vacuous_decode_exit_730.py, 6 passed,
built on the specimen's own numbers (13777 tok, 183.6 s). Mutation-proven:
restoring the vacuous branch turns 4 red. Can-fails pin that a REAL drain still
reads as completion, that the two paths never share a verdict word, and that a
running bundle is still refused mid-flight -- a fix that renamed the healthy
path would make every green window look like a defect.
REGRESSION managers 19 failed / 2415 passed against a baseline of 19 / 2409
captured on the reverted tree: ZERO new failures, +6 are these.
NOTE FOR THE TRAIN, unrelated to this fix: the desk train's managers baseline is
19, against 12 on train/0817-exec. The extra seven are
test_kv_arena_handle_retention_631 (7) and test_kv_arena_span_ops_631 (1), with
test_collective_family_siblings_610 at 3 rather than 2 -- pre-existing on this
composition and not touched here.
efschu
added a commit
to efschu/htsglang
that referenced
this pull request
Aug 17, 2026
…ion pass Records the two-file deletion set (pin_ledger stays, kept and extended by the reconciliation), the per-hunk authority, the three incoherences the textual merge hid, and the candidate verdicts -- notably audit/stale-gates, which merged clean and was dropped because it carries a revert of sgl-project#713 that removes a PhasePolicyConfig kwarg F4-r4's sgl-project#730 tests depend on. Gate at or better than every established count; managers improved on 22.
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.
No description provided.