Conversation
5 tasks
efschu
pushed a commit
to efschu/htsglang
that referenced
this pull request
Aug 29, 2026
sgl-project#798 calls itself "RANK-AGREED BY CONSTRUCTION" and it is -- for the DECISION. What it does afterwards is not. `_pp_void_own_batch` deliberately leaves `running_mbs` alone, "because the pass simply did not run, and it decodes again next pass from the state it still holds". That retention is taken rank-locally, it changes what the SLOT MEANS for the group, and nobody tells the upstream. Boot 46 read the result: sender and receiver both on slot 1, naming two DIFFERENT requests -- ('054d07eb', 8192, 8470) = 278 rows against ('d72fbd70', 8192, 8494) = 302 tokens. Each side internally consistent; both identity checks passed, because `mb_id` is the slot and not the occupant. The surplus-receive reading of the same shape is excluded: it needs the receiver BEHIND in slot index, and acceptance at :9017 proves the indices were equal. Unconditional retention keeps a corpse -- once the upstream has moved the slot on, nothing will ever be computed for the held request again, so the retention protects no live work, only itself. Unconditional release is equally wrong, and that is why this is not a revert: while the upstream still names the held request, its resident decode work is exactly what the void was written to preserve. The condition is the fix. The signal is already on the wire, so this reads and adds nothing: `_pp_admission_incoming_effective` is the upstream's rid set for the pass, and it is reset to None unconditionally at the top of every pass ("a pass that receives nothing must inherit neither half"), so a stale read is impossible by construction and no freshness stamp is needed. WHAT IS CUT HERE IS THE CONDITION, NOT THE RELEASE, and not out of caution in general. `pp_queue_orphaned_chunked_req` carries an explicit legality argument for a request displaced out of `self.chunked_req` -- "no door leads to it at all". A resident decode request is not that animal: it is reachable through `running_mbs`, and queueing it would be the double admission the same docstring prohibits. Dropping wedged (corpse R), refusing wedged (sgl-project#995); a third form that double-admits would be the third bill. Which of the two kinds occupies the slot at the moment of divergence cannot be read from the desk, so the probe reports it, and that field decides the shape of the release. Denominator incremented before any return, every exit a named reason, every reason counted -- so "did not fire" stays separable from "was never asked". Emitted on the existing off-path admission site beside sgl-project#998/#997d, never on the receive path. Evidence: desk, executed. All six exits reachable plus out-of-range; MOVED-ON can fire; seen == sum(reasons) == 8. Belegstufe: DESK-BEWIESEN.
efschu
pushed a commit
to efschu/htsglang
that referenced
this pull request
Aug 29, 2026
…was measured first sgl-project#1000 asked the wrong field. `_pp_admission_incoming_effective` carries rids and is provably fresh, and it is EMPTY on every pass that is not an admission: boot 47 counted 4361 empty against 8 voids, and the branch "occupant held AND decision non-empty" never occurred once in 4372 passes. A field that carries the right quantity and is empty on the path in question does not answer the question. Freshness was checked; POPULATION was not. That check now runs before the build, not after the boot. The carrier was already there, and the send site already reads it: `_pp_send_admission_decision(..., launched=self.mbs[mb_id] is not None, ...)` is evaluated after `self.mbs[mb_id] = plan.batch_to_run`, so the occupant of this pass is in scope at exactly that point -- reduced to a bool. This puts the identity beside the bool. The message states its own population as a contract ("SENT EVERY PASS, EVEN WHEN EMPTY") and is never gated on rank position, and boot 47 measured it independently at 4361/4372 arrivals. Cost, named before building: one dict key, at most eight rid strings, on a message that already travels every pass. No new wire, no new rendezvous, no arity change -- the same extension pattern sgl-project#978 used for its launched chain, with an absent key reading as legacy behaviour. Sentinel kept apart and proven over the real codec: absent key -> None ("this sender said nothing" -- PP0, a legacy sender, a pass that heard nothing); empty tuple -> "I hold nothing", a legitimate answer. They do not collide. Still acts on nothing. The release stays uncut until the specimen says whether the occupant is a chunked continuation (where the existing mover's legality argument covers it) or resident decode work (where it does not). Evidence: desk, executed. Six exits reachable, seen == sum(reasons) == 6, sender helper returns (), ('x','y') and () out of range, sentinel round-trip checked. Belegstufe: DESK-BEWIESEN.
efschu
pushed a commit
to efschu/htsglang
that referenced
this pull request
Sep 1, 2026
…ot end a pass PP0 launched `_pp_void_retracted_pass` let ONE downstream rank decide that the GROUP's pass ran nowhere. Its own docstring named the return trip that made that safe -- "the void output carries the observed local match home, and PP0's guard learns it as a floor" -- and sgl-project#969 CUT V had already deleted that emitter (`_PP_VOID_OUTPUT_KEY`: zero originating senders at ca0ee3a). The verdict therefore travelled downstream only. PP0's `mbs[slot]` stayed set while the last rank's did not, so no output was ever sent and PP0 blocked in `_do_recv` until the deadman -- the exact invariant `_do_recv`'s own comment relies on ("sender and receiver ask one question of one batch"). Measured, twice, and the second is on the stall second itself: 1068cap 07:34:02-09 sgl-project#797 void on rank 1 ONLY (no void/retract line on PP0 or PP2); PP0 parked, PP2 spinning. 1069cohort 08:00:54/55 sgl-project#791 unhonourable on PP1, told=12493 local=8397 then told=13399 local=12493 -- `local` exactly one pass behind `told`. After 08:00:55 only ranks 1 and 2 emit at all (slot_occupant / output_fill / width_agreement run to the takedown at 08:13:32, 4177 and 7973 lines; rank 0 emits nothing). That last measurement also refutes the occupant-sleep node as the halting member: ranks 1 and 2 are alive and turning; the `sgl-project#1000 SLOT-OCCUPANT reasons={'no-statement'}` spin is an INERT probe whose carrier sgl-project#1015 EDIT-F made permanently None. The only halting member is PP0's unbounded output receive. Repairing the return trip would repair a compensation layer for a rank-local verdict, which is the arc the sgl-project#968 order forbids continuing; under upstream-minimal the repair carries the burden of proof and the deletion does not. So the verdict is deleted and the disagreement is DETECTED instead (RAENGE-NIE-UNEINS: a detected divergence stops the group, never a compensating wait): * `_pp_assert_told_honourable` replaces it -- an unhonourable told names rank, slot, rid, told and local and raises. No clamp: clamping to this rank's own local match is rank-local geometry, i.e. sgl-project#631. * The chain-receive throttle arm gets a horizon (SGLANG_PP_OCCUPANT_HORIZON_S, default 90 s, 0 disables) and a named stop. Taking the arm is legitimate and frequent; outliving it never is. * `PpChainReceiver.recv` is bounded the way its sibling `consume_up_to` already was (runaway guard + reported counter), and the launcher now sets SGLANG_PP_CHAIN_RECV_STALL_S=60 -- the sgl-project#824 mechanism has existed since 2026-08-24 and shipped disabled by default, which is why it never fired in either stall. (A-i) is WITHDRAWN rather than built: its counter proof is blind at that site (the rendezvous bumps `sent` only on recv entry) and the DEFER one-shot is itself compensation for the rank-local verdict this commit deletes, so its trigger is removed at the source. Its two red-first tests are replaced by zombie tests for the deletion. Desk evidence: hermetic import + AST (deleted verdict absent, watchman and horizon present, recv bounded); test_968_deletion_falsifiers 24 passed, 1 failed -- test_C_the_void_relay_is_wired_or_deleted_but_never_half_built, which stays red until the relay SYMBOLS are swept out too. The relay is already unreachable at runtime (no rank originates a void any more, and `_pp_absorb_void_output` has no caller in production), so that sweep is a dead-code deletion scheduled beside this commit, not a runtime dependency of it. Belegstufe: DESK-BEWIESEN. Boot pending.
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.
Motivation
This should not be needed at the moment, just make a backup, do not merge.
Modification
Briefly describe the changes made in this PR.
Checklist
pre-commit run --all-filesor other linting tools are used to fix potential lint issues.CI States
Latest PR Test (Base): ❌ Missing
run-cilabel -- add it to run CI tests.Latest PR Test (Extra): ❌ Blocked --
run-ciis required first.