Prebuilt: finish the PR set repin - #41
Merged
Merged
Conversation
#39 landed the first pin refresh only, so master still points at commits that have since moved on and that conflict with each other. ggml-org ggml-org#24523 was force-pushed: it now places LLM_ARCH_MINIMAX_M3 next to LLM_ARCH_MINIMAX_M2 rather than at the tail of the enum, matching how llama-arch.cpp already groups the name table. That removes the src/llama-arch.h half of its collision with ggml-org#25731, which appends LLM_ARCH_INKLING at the tail. New head baee0f5. ggml-org ggml-org#25731 has picked up current master and the thinking_end_tags rename, so it now builds on its own against b10133 and newer. Its entry is replaced by unslothai #40, which carries what is still unresolvable between the two: both add a chat parser and a detection block in the same region of common/chat.cpp, immediately before "namespace workaround {". chat.cpp has no MiniMax-M2 parser to sit beside, so there is no principled alternative anchor for that half. Replaying the resolver sequence on b10133: OK ggml-org ggml-org#24423 @ c3fb972 OK ggml-org ggml-org#24523 @ baee0f5 OK unslothai #40 @ 233cedb Drop the #40 entry and repin ggml-org#25731 upstream once either PR lands.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #39, which landed only the first of three commits, so master still pins commits that have since moved on and that conflict with each other.
Master today:
What changed on the two upstream PRs
ggml-org#24523 now places
LLM_ARCH_MINIMAX_M3next toLLM_ARCH_MINIMAX_M2instead of at the tail of the enum, matching howllama-arch.cppalready groups the name table. That removes thesrc/llama-arch.hhalf of its collision with ggml-org#25731, which appendsLLM_ARCH_INKLINGat the tail. New headbaee0f5b2.ggml-org#25731 has picked up current master and the
thinking_end_tagsrename, so it now builds on its own againstb10133and newer. It previously did not: upstream 910196f renamedcommon_chat_params::thinking_end_tagto a vector, and that PR still assigned the old scalar.What #40 still carries
Only the
common/chat.cpphalf. Both PRs add a chat parser and a detection block in the same region, immediately beforenamespace workaround {. Unlike the enum, there is no principled alternative anchor:chat.cpphas no MiniMax-M2 parser for MiniMax-M3 to sit beside, so relocating one would be arbitrary and would break again on the next upstream edit near it.Verification
Replaying the resolver sequence on
b10133:All three pins pass the membership check (21, 5 and 5 commits respectively, all under the 250 cap, each pin equal to its PR head). The merged tree is API-consistent:
chat.hdeclaresthinking_end_tags, and no scalar assignment remains.llama,llama-common,test-llama-archsandtest-chatbuild against the merged tree with zero errors.test-chatpasses;test-llama-archsexits 0 withminimax-m3at 0.00e+00.Drop the #40 entry and repin ggml-org#25731 upstream once either PR lands.