contract(qwen3-moe-forward-gpu-v1): v1.6.0 → v1.7.0 — DRAFT → ACTIVE_ALGORITHM_LEVEL#1530
Merged
noahgift merged 1 commit intoMay 6, 2026
Merged
Conversation
…ALGORITHM_LEVEL post 1.x cascade Status promotion amendment after the M-GPU-MOE-1.4 step (c) cascade closure (v1.6.0 / aprender PR #1529). What flips: - metadata.status: DRAFT → ACTIVE_ALGORITHM_LEVEL - M-GPU-MOE-1 implementation_stage (umbrella): PENDING → SHIPPED (covers full 1.x sub-cascade 1.0 → 1.4 step c) - metadata.status comment refreshed (was stale "Scaffold + architecture amendments + preload-bug fix") Why ACTIVE_ALGORITHM_LEVEL not ACTIVE_RUNTIME: Mirrors CPU sibling qwen3-moe-forward-v1 cadence — ALGORITHM_LEVEL = "algorithm bound on main; finite output for canonical prompt". RUNTIME flip waits on M-GPU-MOE-3 (throughput ≥150 tok/s + memory budget) per original v1.0 contract convention. Per-AC status: - AC_GPU_MOE_001 (cosine ≥0.99 vs CPU): ALGORITHM_LEVEL_DISCHARGED - AC_GPU_MOE_002 (cosine ≥0.99 vs HF FP16): blocked on fixture - AC_GPU_MOE_003 (top-5 token recovery): pending heavy re-run - AC_GPU_MOE_004 (output finiteness): DISCHARGED (M85) - AC_GPU_MOE_005 (deterministic per-token): ALGORITHM_LEVEL_DISCHARGED - AC_GPU_MOE_006 (throughput ≥150 tok/s): PENDING M-GPU-MOE-3 - AC_GPU_MOE_007 (VRAM ≤95%): PENDING M-GPU-MOE-3 YAML-only — production hot paths byte-unchanged. `pv validate` 0/0. Co-Authored-By: Claude Opus 4.7 <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Status promotion amendment after the M-GPU-MOE-1.4 step (c) cascade closure (v1.6.0 / aprender PR #1529 squash
89cb26af7).What flips
metadata.statusDRAFTACTIVE_ALGORITHM_LEVELmetadata.statuscommentM-GPU-MOE-1implementation_stagePENDINGSHIPPED(umbrella covers 1.0 → 1.4 step c)Why ACTIVE_ALGORITHM_LEVEL not ACTIVE_RUNTIME
Mirrors CPU sibling
qwen3-moe-forward-v1cadence —ALGORITHM_LEVEL= "algorithm bound on main; finite output for canonical prompt".ACTIVE_RUNTIMEflip waits on M-GPU-MOE-3 (throughput ≥150 tok/s + memory budget) per original v1.0 contract convention.Per-AC status
4/5 algorithm-bound + 1 fixture-blocked → ACTIVE_ALGORITHM_LEVEL threshold crossed.
Sub-cascade pinned in M-GPU-MOE-1 SHIPPED
What stays PENDING
Test plan
pv validate0/0🤖 Generated with Claude Code