Repository navigation
Description
Current state: Existing Issue author @fake0fan has submitted PR #351, now 1694a0b, but this Issue still records Proposed, unassigned ownership and no accepted implementation delegation. The PR now contains the six content/coverage files plus 80 regenerated packaged knowledge files, and keeps Refs #348 rather than closure wording. At the prior 18c9a16 head, Ready had four software-check failures from stale packaged projections (including the reported 6 failed / 3538 passed full-check result). The 1694a0b5 incremental review clears the stale-index delta by static inspection; the subsequent current-head Ready result now has all six jobs passing, including both full-check and installed-package versions. This supersedes the earlier pending/full-check failure state, not the remaining review questions. The exact-head declaration now names claude-opus-5 and claude-opus-5-5 with effort unknown and extends its exception request to the generated records. The policy check still fails: explicit independent owner exception approval is absent, material AI author 1's model is unapproved, and author 2's effort is not allowed. The reviewer also retains the source/provenance-marker questions, blog-figure sourcing, and branch-only source-pin integration question; no merge strategy or new acceptance policy is chosen here. Source/index consistency and CI do not establish model/performance efficacy, acceptance or authority to close this Issue.
Decision needed: The requester/maintainers need to record the accepted scope/delegation and name the accountable and acceptance owners, which remain TBD below, including the existing gate-ownership/cross-link question. A submitted PR or reviewer's suggestions do not make those decisions.
Next action: Existing PR author @fake0fan retains the remaining source clarification and re-review work, accurate revision-specific documentation, and any exact-head policy-exception request to an authorized independent owner. The generated/packaged-consistency failure is no longer an outstanding repair at 1694a0b. Preserve the original proposed scope and acceptance text below; this status grants no implementation, policy-exception, merge or closure authority.
Goal and acceptance
methods/performance-ceiling-analysis L1 turns a model config plus a hardware
table entry into a runtime floor. It gates neither half of the demand side: the
skill has no procedure for checking that the weight and KV counts it divides by a
peak describe the model actually being deployed. safetensors appears nowhere
under this owner, while the mechanics already exist next door in
weight-loading-optimization
and a byte-level weight inventory already exists as an artifact pattern under
h3-c.
An L1 floor computed from a wrong parameter count is wrong in a way no roofline
check detects, because the roofline never looks at the model again. This issue
adds the missing prerequisite and records the external source it is derived from.
- Problem / desired outcome: a reviewed-source prerequisite that anchors L1's
weight demand against the checkpoint before any number derived from it is
reported, with its blind spot stated rather than implied. - Completion criteria:
- A reference document and a typed
source-identity.jsonunder
methods/performance-ceiling-analysis/references/, recording the pinned
commit, per-file git blob and sha256 digests, and the verbatim-vs-summary
coverage of each inspected source. - A prerequisite step in
SKILL.mdcovering two gates: the bidirectional
per-tensor checkpoint join, and the per-rank weight ledger. The first needs no
parallelism layout; passing it certifies nothing about per-rank bytes. - An explicit statement of what the weight anchor does not anchor (KV
semantics: a windowed and a global attention with the same head dims have
byte-identical weights). - A
metadata.jsonsource entry and adocs/reference-matrix.mdrow. locally_verifiedstaysfalse;empirical_validationstaysnot_run.
- A reference document and a typed
Scope and constraints
- In scope: documentation and skill-library content under the existing
performance-ceiling-analysisowner, plus the two matrices' source rows. - Out of scope:
- The bound model proposed in [RFC] Per-task SOL modeling and a KDA-flow gap metric for fused operators #303. This issue adds a prerequisite check, not a
bound, and does not depend on [RFC] Per-task SOL modeling and a KDA-flow gap metric for fused operators #303 being accepted. - The
Class A/Class Bvocabulary of [RFC] Per-task SOL modeling and a KDA-flow gap metric for fused operators #303. Note for reviewers: the cited
source usesClass A–Class Efor an unrelated taxonomy (verification rule
kinds), so neither vocabulary should be imported alongside the other. - Importing or vendoring any measured kernel corpus. External measurement data
stays a reference with stated availability, per the
knowledge-base contract. - Any new skill ID, registry entry or
skill-index.jsonchange. - Any measurement, benchmark or performance claim.
- The bound model proposed in [RFC] Per-task SOL modeling and a KDA-flow gap metric for fused operators #303. This issue adds a prerequisite check, not a
- Relevant dependencies, shared interfaces or limits:
weight-loading-optimization
keeps ownership of loading mechanics; this issue adds only the correctness gate
and cross-links it.
Ownership and authorization
- Proposed by / actual requester: repository owner
- Status: Proposed
- Accountable parent (Issue-level owner, if assigned): TBD
- Slice implementer(s) / acting contributor (if assigned): TBD
- Goal-acceptance owner: TBD
- Accepted decision or scoped delegation: Not yet granted
Inputs and deliverables
- Relevant sources, revisions or linked issues:
github.com/shenh10/HuggingArch@facbbbc96856e558b9084a94a5070b2e2c86cf0b
(MIT; singleinit repocommit dated 2026-11-04T02:24:14Z), inspected
2026-11-04. Readset:docs/validation.md,docs/measured_calibration.md,
docs/evaluation_model.md,docs/known_limitations.md,
backend/arch/validate/_matching.py,backend/arch/validate/_weight_ledger.py,
backend/arch/validate/_ablation.py,backend/measure/scope.py,
kernel_bench/emit.py.- A companion blog post dated 2026-10-08, read in part. The repository
post-dates it by roughly four weeks and carries no history, so the post's
figures are not attributable to this commit and are recorded as unverified
where they are recorded at all. - Related: [RFC] Per-task SOL modeling and a KDA-flow gap metric for fused operators #303 (proposed; not a dependency of this issue).
- Expected artifacts: one PR touching only the files named under completion
criteria.
Completion and closure
- Who accepts completion and may close: the named acceptance owner, not the PR merge.
- Remaining uncertainty / next decision: whether the two gates belong to this
owner alone or should be cross-declared as a reference from
weight-loading-optimization; the PR proposes the former with a cross-link.
Activity
amy-why-3459 commentedon Nov 4, 2026
Thanks, the scoping here is clear, and separating "the weight anchor certifies X" from "it says nothing about KV semantics" is the right framing. A few points to settle before a PR:
weight-loading-optimizationalready owns the safetensors mechanics (references/fastsafetensors-transfer-readset.md). I agree with putting the correctness gate underperformance-ceiling-analysis, since that's where the L1 number gets consumed, but please make the cross-link go both ways so the loading skill doesn't end up growing a second, slightly different checkpoint-inventory procedure.repositories/h3-c/audit-h3-runtime-residency/references/minimax-h3-weight-inventory.jsonis already a byte-level inventory. Will the per-tensor join reuse that schema (or name the fields it shares with it), rather than adding a new one? One shape would make the two artifacts comparable.SKILL.mdentirely, not just marked unverified, so they can't get quoted as numbers later.The out-of-scope list (no #303 bound model, no Class A/B vocabulary,
locally_verified: false) looks right to me.docs: anchor L1 weight demand against the checkpoint
Dong1017 commentedon Nov 16, 2026
Decision — Accept L1 weight-anchor scope (Dong-bot as @Dong1017 delegate)
Recorded 2026-11-16. Authority: Dong-bot decision authority for
@Dong1017accept/decide. Thread basis: issue Goal/acceptance + Completion criteria; Amy scoping notes (6626759642); delivery PR #351 at head126a0e6e447cf3184ef90a2dad06606325f33f8a(Amy APPROVED / PASS on that head).Accepted — bounded knowledge delivery
Accept this issue’s stated Goal/acceptance and Completion criteria as the authorized delivery for anchoring L1 weight demand against the checkpoint under
methods/performance-ceiling-analysis:source-identity.json(pinned commit, per-file blob/sha256, coverage).SKILL.md: bidirectional per-tensor checkpoint join; per-rank weight ledger (gate 1 alone certifies nothing per rank).metadata.jsonsource entry +docs/reference-matrix.mdrow.locally_verified: false;empirical_validation: not_run.Accepted — gate ownership / cross-link
Correctness gates live under
performance-ceiling-analysis(where L1 consumes the number). Keep a bidirectional cross-link withweight-loading-optimizationso loading mechanics stay owned there and do not grow a second inventory procedure (Amy point 1).Confirmed — ownership (was TBD)
Still open (not granted by this accept)
SKILL.md) — treat as delivery/review checklist on docs: anchor L1 weight demand against the checkpoint in performance-ceiling-analysis #351; Amy’s current-head PASS is evidence they are satisfied for that head, not a substitute for acceptance-owner closure here.Status
Flipping
status:proposed→status:accepted. Next action for delivery: finish #351 review/merge lane; acceptance owner closes #348 only after Completion criteria are verified on the merged revision.Dong1017 commentedon Nov 16, 2026
Post-merge acceptance check (#351 → main)
Checked after squash-merge of #351 by @Dong1017 onto
mainatf536288710c726a827bfa3e4357c2c911984cbc3(merged head content from126a0e6e447cf3184ef90a2dad06606325f33f8a). Goal-acceptance owner: @Dong1017. PR wording wasRefs #348(merge alone does not close).Completion criteria on merged revision
f5362887source-identity.jsonundermethods/performance-ceiling-analysis/references/huggingarch-checkpoint-anchor.md+huggingarch-source-identity.json(pinfacbbbc9…, per-file blob/sha256, inspection coverage)SKILL.md(per-tensor join + per-rank ledger)SKILL.mdand the anchormetadata.jsonsource entry +docs/reference-matrix.mdrowlocally_verified: false;empirical_validation: not_runRemaining — blocks closure
Bidirectional cross-link with
weight-loading-optimizationis incomplete.Accepted ownership decision (6905865813) required gates under
performance-ceiling-analysisand a bidirectional cross-link so loading mechanics stay owned by WLO (Amy point 1).references/huggingarch-checkpoint-anchor.md(“Loading mechanics stay with weight-loading-optimization”).methods/weight-loading-optimization/(SKILL.md,metadata.json, or a short reference note). docs: anchor L1 weight demand against the checkpoint in performance-ceiling-analysis #351’s 9 files did not touch WLO.Until that reverse link lands on
main, this Issue stays open. No other Issues are closed by #351 (Refs #348only; #303 / #385 / #386 remain separate scope).Next
Small follow-up PR (or amendment) adding the WLO →
performance-ceiling-analysis/huggingarch-checkpoint-anchorcross-link; then re-check closure here. Branch-only source-pin / squash limitation stays documented and is not the closure blocker.Dong1017 commentedon Nov 16, 2026
Next-step assignment (WLO → PCA)
Follow-up to the post-merge check (6905998770) — no change to that gap analysis.
Remaining acceptance gap (unchanged): WLO → PCA /
huggingarch-checkpoint-anchorreverse cross-link undermethods/weight-loading-optimization/is still missing onmain. Knowledge criteria from #351 are otherwise met.Who lands it: @fake0fan as slice implementer for the original delivery — please open a small follow-up PR that adds only the WLO →
performance-ceiling-analysis/ checkpoint-anchor pointer (SKILL.md,metadata.json, or a short reference note). Do not reopen scope beyond that reverse link.Closure: @Dong1017 (goal-acceptance owner) keeps #348 open until that reverse link is on
mainand re-checked here. Merge of #351 alone does not close.