[Release] Resume public development from latest private main - #342
Merged
yangzhuxinyzx merged 5 commits intoAug 27, 2026
Merged
Conversation
Source-audited against private main b06f54c. Includes strict route/shape admission, bitwise-equivalent long-context kernel optimizations, static-gate fixes, default-on promotion, and explicit rollback. Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>
Extends the quality-valid max-aware D256 GQA architecture to KV256K, removes the rejected raw-logit half2 experiment, preserves explicit rollback, and retains the recorded exact output hash with 19.5% prompt-throughput gain. Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>
Default the audited non-fused shared-gate QPN8 and exact TP4 six-route MXFP4 QPN M1 paths with explicit rollback and old-extension fallback. Preserve the recorded PP2 x TP4 endpoint, rejected-path evidence, and long-context design scope. Tests: Ruff 0.16.4; clang-format 21; git diff --check; 39 passed, 4 skipped policy tests; recorded matching-extension suite 41 passed. Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>
This reverts commit f4c3451. Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>
Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>
yangzhuxinyzx
marked this pull request as ready for review
August 27, 2026 14:29
This was referenced Aug 27, 2026
yangzhuxinyzx
added a commit
that referenced
this pull request
Aug 27, 2026
#342 已导入稳定的 256K D256 GQA 实现,并明确排除导致零 token 的 half2 实验。 Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.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
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.
Purpose
Resume public development after leadership approval while preserving the v1.3.0 release tag and all public history.
Integration contract
Test Plan
This is a history-preserving publication change. Validate exact tree identity and reuse the focused source, numerical, and operator gates already recorded for the three accepted private changes. Do not repeat expensive end-to-end runs.
Test Result
Risk and rollback
The displayed diff is intentionally large because #329 replaced the development tree with the v1.3.0 snapshot. This PR reverses that snapshot commit through ordinary history and then imports the audited private main. The v1.3.0 tag and release artifacts remain intact.
AI assistance was used for repository inventory, exact-tree verification, and preparing this publication PR. Human review remains required before promotion.
Signed-off-by: yangzhuxinyzx 153831768+yangzhuxinyzx@users.noreply.github.com