quant : fix quantizing moe with mtp#24986
Merged
Merged
Conversation
papamoose
pushed a commit
to papamoose/llama.cpp
that referenced
this pull request
Jun 27, 2026
LyndonBlack
added a commit
to LyndonBlack/llama.cpp-Ternary-1.58Bit-and-TurboQuant
that referenced
this pull request
Jul 5, 2026
Key upstream additions preserved alongside turboquant modifications: - EAGLE3 speculative decoding support (ggml-org#18039) - Eagle3 for Qwen3.5 & 3.6 (ggml-org#24593) - Flash MTP3 support (ggml-org#24340) - MoE+MTP quantization fix (ggml-org#24986) - New models: Granite Speech Plus, Cohere2-MoE - mtmd batching API and OCR support - KV cache sharing framework (mem_other, layer_share_cb) - Various CUDA optimizations and server improvements All entropy-adaptive KV cache, turboquant types, and TURBO_K_Q8 env var features preserved in merge.
adrianhoehne
pushed a commit
to adrianhoehne/llama.cpp
that referenced
this pull request
Jul 5, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
Fixes #24379
Fixes #24661
Additional information
Due to the following check and the fact that
n_layer()instead ofn_layer_allwas being used it was impossible to quantize MoEs with MTP.llama.cpp/src/llama-quant.cpp
Lines 430 to 432 in e5c3ac4
Supersedes #24832
Requirements