repin GLM-5-Next to the current head of ggml-org#27754 - #159
Merged
Conversation
The pin was 50 commits behind the PR head and sat before "Add MTP support", so the nightly shipped GLM-5-Next without the NextN draft head, without the master merge, and without the pooled-key shift fix. Verified against b10705 by replaying the resolve step: the new commit fetches from ggml-org, is a commit of ggml-org#27754, and merges onto the base plus the pins listed before it with no conflict. Unrelated, and not fixed here: ggml-org#25731 stops merging at b10705. Upstream ggml-org#27960 touched ggml/src/ggml-rpc/ggml-rpc.cpp, which the Inkling branch also edits, and additive_merge.py correctly refuses it. It merges on b10698, the base of the last shipped nightly, so the next run on a newer base will fail there until that branch is merged forward.
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
danielhanchen
added a commit
that referenced
this pull request
Aug 31, 2026
* unsloth: pin ggml-org#27941, #152 and #154 ggml-org#27941 at 02eb201, no longer a draft and MERGEABLE upstream. It fixes four qwen4exp correctness defects and is the only account of the Flash-Next reporter who is on Vulkan only, where the allocator variable is never set. The previous pin PR #148 carried the stale 8161d11 and is closed. #152 at 258345e and #154 at 31e432e both merge onto b10708 on their own. #137 is already pinned at 4e1865e, which is still its head, so no change. #142 and #144 are NOT pinned here: both predate an upstream refactor that folded lazy_mode and model_shared into a lazy struct, so they conflict on src/llama.cpp and src/llama-model-loader.cpp against b10708. b10708 has 'ml.lazy.mode = params.lazy_mode' where those branches still write 'ml.lazy_mode' and 'ml.model_shared'. They need rebasing onto current upstream before they can be pinned; pinning them now would fail the resolve. * unsloth: repin ggml-org#27941 to 6b2b85c The PR moved on at 10:44Z, after 02eb201 was pinned. Verified to merge onto the current base tag: 6 files changed, 480 insertions, 138 deletions. * unsloth: pin #144, rebased, and leave #142 out as contained in it #144 rebased onto b10709 at 6fc8df1. Two of its nine commits were dropped rather than carried: 'qwen4exp: fix QSA correctness defects and harden metadata loading' and the comment tidy on top of it. That work is what ggml-org#27941 supersedes, and keeping both copies is what made the two pins conflict in llama-kv-cells.h and llama-memory-hybrid-idx.cpp. Listed after ggml-org#27941 so the upstream version of that work lands first. #142 is deliberately NOT pinned: its single commit is byte-identical to #144's c7bd6f2 apart from the lazy API spelling, so #144 already contains it and pinning both would apply the same change twice. Verified: b10709 + ggml-org#27941 + #144 merges clean, 24 files, +612/-94. * unsloth: repin ggml-org#27754 to 949f7ef The PR moved on at 10:39Z; 5796547 was pinned by #159 earlier today. Verified to merge onto b10709: 44 files changed, 2673 insertions, 38 deletions. Every entry in the set is now at its PR's current head. --------- Co-authored-by: danielhanchen <elliegouldingstuff@gmail.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.
The GLM-5-Next pin was 50 commits behind the head of ggml-org#27754, and sat before
d07e71ede Add MTP support. The nightly has therefore been shipping GLM-5-Next without the NextN draft head, without the master merge, and without the pooled-key shift fix.Verification
Replayed the resolve step against
b10705(the tag the aging rule selects right now): checked out the base, merged the pins in listed order with--no-ff -c merge.conflictStyle=diff3, and ranadditive_merge.pyon any conflict.Both resolve gates pass on the new commit: it fetches directly from
ggml-org, and it is present in thepulls/27754/commitslisting.On the merged tree, MTP measured 1.29x on GLM-5.3-Flash UD-IQ1_S (61.5 -> 79.3 t/s,
--spec-draft-n-max 3, draft acceptance 0.634). 1-chunk wikitext perplexity is unchanged at 3.3749 +/- 0.40867.Separate issue, not addressed here
ggml-org#25731(TML Inkling) no longer merges atb10705. Upstream ggml-org#27960 touchedggml/src/ggml-rpc/ggml-rpc.cpp, which the Inkling branch also edits, soadditive_merge.pyrefuses it:It still merges on
b10698, the base of the last shipped nightly, which is why runs are currently green. The next run on a base at or pastb10705will fail on that pin regardless of this change. It needs the Inkling branch merged forward.