You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Tracking epic for the dedicated, non-cadence milestoneInference dispatch & architecture consolidation — everything under #3418's umbrella too large-blast-radius
for a 06x train. Two sub-projects, two specs, one milestone, one epic:
Placement: this milestone has no train-leaves-by deadline (unlike the 06x
cadence). Both sub-projects touch the same forward/dispatch paths that carry
aprender's one proven GPU-parity receipt (Qwen2.5-Coder, docs/BEATS.md) once past
their low-risk Phase 0/1 design work — that's why they're here instead of on 0.69/0.70.
Operator triage note: #3422, #3423 and PR #3424 were moved into 0.70.0 by this morning's milestone triage run, and have been reverted to this dedicated milestone on reading your body — the no-train-deadline placement stands. No other field was touched.
Not scheduled by 30-day-plan.md v2.2 — and that is a decision, not an oversight
This epic sits on its own milestone ("Inference dispatch & architecture consolidation", 3 open) and the 30-day plan does not allocate a slot to it. Recording why, so nobody reads the silence as an accident.
Its subject matter is being done, under a different name and a narrower scope. The plan's §5.1 / §5.7 deliver the part of "dispatch consolidation" that a release train can hold:
G1/G2 format gates — bit-exact container round-trip, then requant cosine over live types at the pin.
What this epic adds beyond those is the wider architectural consolidation (#3422: shared attention/FFN building blocks exist and are 0% adopted). That is real, and it is the kind of work that is invisible at a 72-hour takt: it touches every architecture, it cannot be landed behind one must-carry row, and the plan's own capacity note is that C is ~29 merged PRs per train with C itself [U].
Consequences under current doctrine:
Rule 3 — if this is ever proposed as a must-carry row, it needs a ruled plan and a falsifier proven satisfiable by a RED test on mainbefore that train opens. Today it has neither.
Rule 9 — the train exclusion predicates are label-based (arch-model-new, gate-framework-new, …). A consolidation epic is not excluded by them, which means it could drift into a train by default. It should not arrive that way.
Its own milestone has no due date, which the plan treats as the correct shape for a bucket that is not a train (cf. 0.73, which is being renamed backlog for exactly this reason).
Recommendation for the team review: either give this epic a dedicated cycle after the month's spine lands (the plan's spine is E → G → B → A → I, and this is a G/B substrate change), or decompose it into rows that individual trains can carry behind their must-carry. Leaving it as an unscheduled epic with three open children is the state most likely to produce a surprise PR mid-train.
Superseded by EPIC E7 #4001 (APR-EPIC-001 A4). Open children re-parented: none. Owner lines copied to the absorbing epic's body. Applied by aprender-d1: claude+agy both said close, apr shadow row recorded (handoff/close-quorum-2026-09-25.json).
Activity
docs(spec): PP-QUANT-001 — cross-link downstream PP-ARCH-001, close o…
[-]EPIC: PP-ARCH-001 — shared-block forward-path consolidation (dedicated cycle)[/-][+]EPIC: Inference dispatch & architecture consolidation (dedicated cycle)[/+]docs(spec): PP-QUANT-001 — Phase 2/3 gets its real milestone, not "ma…
docs(spec): PP-ARCH-001 — reflect ticket/epic consolidation (#3422)
PMAT-3427: roadmap rows arrive as fragments; an owed contract is name…
noahgift commentedon Sep 17, 2026
Operator triage note: #3422, #3423 and PR #3424 were moved into 0.70.0 by this morning's milestone triage run, and have been reverted to this dedicated milestone on reading your body — the no-train-deadline placement stands. No other field was touched.
noahgift commentedon Sep 20, 2026
Not scheduled by
30-day-plan.mdv2.2 — and that is a decision, not an oversightThis epic sits on its own milestone ("Inference dispatch & architecture consolidation", 3 open) and the 30-day plan does not allocate a slot to it. Recording why, so nobody reads the silence as an accident.
Its subject matter is being done, under a different name and a narrower scope. The plan's §5.1 / §5.7 deliver the part of "dispatch consolidation" that a release train can hold:
#[repr(u32)] GgmlType+TRAITS[43]verified against upstream ggml at the pinned sha — EPIC: PP-QUANT-001 — quant-type dispatch, Phase 0/1 (0.69 train) #3421, 0.69's must-carry row;What this epic adds beyond those is the wider architectural consolidation (#3422: shared attention/FFN building blocks exist and are 0% adopted). That is real, and it is the kind of work that is invisible at a 72-hour takt: it touches every architecture, it cannot be landed behind one must-carry row, and the plan's own capacity note is that C is ~29 merged PRs per train with C itself
[U].Consequences under current doctrine:
mainbefore that train opens. Today it has neither.arch-model-new,gate-framework-new, …). A consolidation epic is not excluded by them, which means it could drift into a train by default. It should not arrive that way.backlogfor exactly this reason).Recommendation for the team review: either give this epic a dedicated cycle after the month's spine lands (the plan's spine is E → G → B → A → I, and this is a G/B substrate change), or decompose it into rows that individual trains can carry behind their must-carry. Leaving it as an unscheduled epic with three open children is the state most likely to produce a surprise PR mid-train.
Plan governance: #3080 · 0.70: #3081.
noahgift commentedon Sep 23, 2026
triage 2026-09-23 (aprender-dd, standing triage owner): milestoned to 0.74.0, theme Any Model (architectures, formats); it had no release milestone.
feat(session): one engine — Session<ArchForward> owns generation for …
noahgift commentedon Sep 25, 2026
Superseded by EPIC E7 #4001 (APR-EPIC-001 A4). Open children re-parented: none. Owner lines copied to the absorbing epic's body. Applied by aprender-d1: claude+agy both said close, apr shadow row recorded (handoff/close-quorum-2026-09-25.json).