docs: NUMPOL-CARRIER-1 — the S5 numeric_policy carrier gets an owning queue row - #624
Merged
Merged
Conversation
… queue row The standing decision the substrate view flagged: the generalized below-Graph-IR numeric_policy carrier (Decision #32) had four mandating consumers (CAKE, game-theory fusion-as-correctness, PDE info_loss retirement, AD-JET-IR-1) and no owning row. It is now integrated-plan queue row 3b — carrier design + fail-closed boundary verifier, with the landed W1.1 fragment accumulator as the worked reference, FORGE §1.3's measured realizability verdict as the acceptance target, and explicit parallel-safety with Orders 3/5. CORE_SUBSTRATE_VIEW's two 'no owning row' flags now point at the row. Ordering note: numbered 3b to avoid renumbering Orders 4-14, which are referenced throughout the plan and the audit prose. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 60295acf61
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
…ODOs, bump freshness P1 — the row introduces a shared Schedule→Tile contract, so AGENTS.md L81-85 applies to a plan row exactly as it does to code. New sync key NUMPOL-CARRIER-1-2026-08-24 in all four backend queues, each with an architecture-specific outcome rather than a copied sentence. All four are "follow-up required" — the row is newly owned and nothing is implemented yet, so claiming parity anywhere would be false — but the obligations differ: ROCm owns the worked reference (the W1.1 fragment accumulator, which must be RE-EXPRESSED as an instance, not duplicated, #31); x86 has no carrier at all today and is both consumer and regression gate; NVIDIA must sequence behind its open W1.1 typed-fragment producers or the two collide at the same seam; Apple must not require a third policy representation across its Python-synthesizer / C++-pipeline seam. P2 — the resolved ownership TODOs are retired together with the row that resolved them: CORE_SUBSTRATE_VIEW's "four flagged inputs" paragraph now records S5 as closed (three remain open) so it cannot be re-proposed, and AUTODIFF_NEXTGEN_PLAN's two references (§2.3 key table and the AD-JET-IR-1 gate table) point at queue row 3b instead of "no owning row". The one remaining "no owning row" in that plan is the unrelated vmap/batching_rule item and is deliberately left. P2 — CORE_SUBSTRATE_VIEW frontmatter bumped 2026-08-15 → 2026-08-24 and the owning freshness view regenerated: exactly one line changes (that doc's row, 9 days stale → 0), no date churn elsewhere. test_audit_docs.py green; generated docs in sync. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Owner
Author
|
All three findings verified and fixed in eac5a28. P1 (four-backend assessment) — correct, and the point generalizes: AGENTS.md L81-85 applies to a plan row that introduces a shared contract exactly as it does to code. New sync key
P2 (resolved TODOs) — fixed together with the row that resolved them: P2 (freshness) — confirmed: frontmatter bumped 2026-08-15 → 2026-08-24 and the owning freshness view regenerated. The diff is exactly one line (that doc's row, 9 days stale → 0) with no date churn elsewhere.
🤖 Generated with Claude Code |
gstoner
pushed a commit
that referenced
this pull request
Aug 25, 2026
…an identity, record cross-backend P1 (overlap erased) — CONFIRMED and worse than reported. A 12-action MegaMoE plan inferred all 66 edges of the complete order, so R3 would estimate and prune overlap plans as sequential pipelines. Measured three distinct over-conservatisms in the SHARED inference, each fixed with the sound rule: 1. ordered collectives serialized against every surrounding op. They constrain the order OF COLLECTIVES (all ranks issue them in the same relative order), not unrelated local work — data through a collective is still ordered by SSA/alias/memory edges. Now collective-to- collective only. 2. a registered op declaring `aliasing="none"` had its declaration discarded whenever it was effectful, so every collective result was assumed to alias hidden state and `unknown_alias_fact` became an all-pairs barrier. A declared fact now has its consumer (#29/#30). 3. `has_memory_dependence` returned top for ANY effectful pair. A registered pure op touches no hidden state, so with a disjoint alias set it cannot depend through memory; two pure ops sharing a read-only operand (the weights every expert reads) likewise get no alias edge. Result: 66 → 36 edges, still covering every hand-oracle edge, with the extras now collective-ordering only. `combine:0 -> compute:1` and `compute:0 -> compute:1` are gone; `dispatch:0 -> dispatch:1` and `combine:0 -> combine:1` remain. An existing test asserted the old blanket rule for collectives; it is deliberately replaced by an explicit ordering test (positive: collectives keep relative order; negative: independent local work floats) plus an alias-gated memory-dependence test. The other three barrier classes keep their all-pairs assertion unchanged. P2 (digest identity) — CONFIRMED: action ids and graph shape are functions of the chunk COUNT, so plans differing in capacities/buffers/token ranges/in-flight limit content-addressed identically. The schedule object now binds `plan.artifact_digest`, which already addresses exactly those fields; `candidate_id` stays the plan id so pruning keys are unchanged. P1 (cross-backend) — sync key SO3-INFER-EDGES-2026-08-24 in all four queues: rocm/x86 parity validated (analysis is prune/rank-only; no generated code or numerics change), nvidia/apple not-applicable-today with the inherited-on-adoption reason. Also resolves the merge conflict with #624 by keeping both queue rows. Gates: composition-cost + graph-dataflow + MegaMoE suites 71 pass; mypy 0; ruff clean; generated docs in sync. Co-Authored-By: Claude Fable 5 <noreply@anthropic.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
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.
Closes the standing decision from the compiler-actions review: the S5 generalized
numeric_policycarrier (Decision #32's below-Graph-IR carrier) had four mandating consumers — CAKE (the decision's original derivation), game-theory §6 (fusion is a correctness feature), PDE §III.4 (interimtessera.info_lossrecords), and AD-JET-IR-1 (coefficient/cotangent policy) — and no owning queue row.It is now integrated-plan queue row 3b (NUMPOL-CARRIER-1):
!tile.fragment<…, acc, …>route is the worked reference to generalize, not duplicate (Apple GPU: Gumbel-max inference sampler (#18-safe, reproducible) #31).info_lossrecords retired; FORGE §1.3's measured fused-epilogue realizability verdict (913× → 1.1× → 1.0× as a function of accum × state dtype) decided by the carried policy.CORE_SUBSTRATE_VIEW's two "no owning row" flags now point at the row. Docs-only;test_audit_docs.pygreen.🤖 Generated with Claude Code