llama: prefix MTP assistant tensors with 'mtp.' on load allowing use of -ot 'mtp..*=CUDA0' flag#7
Merged
Ooooze merged 1 commit intoMay 12, 2026
Conversation
When the Gemma 4 assistant GGUF is loaded via llama_model_load_mtp_from_file, its block tensors (blk.0-3.*), token_embd, output_norm and rope_freqs share identical names with the target model's tensors. This makes it impossible to uniquely target MTP assistant tensors via -ot rules for GPU placement. Fix: after loading the assistant into aux, rename all tensors not already prefixed with 'mtp.' to 'mtp.<original_name>'. This is done purely in-memory on the tensors_by_name vector and the ggml_tensor name field — the GGUF file and published arch names are unchanged. After this change, all MTP assistant tensors are addressable as mtp.blk.N.*, mtp.token_embd.weight, mtp.output_norm.weight etc, and can be pinned with: -ot 'mtp\..*=CUDA0'
e381dc9
into
AtomicBot-ai:feature/turboquant-kv-cache
1 check passed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
When the Gemma 4 assistant GGUF is loaded via llama_model_load_mtp_from_file, its block tensors (blk.0-3.*), token_embd, output_norm and rope_freqs share identical names with the target model's tensors. This makes it impossible to uniquely target MTP assistant tensors via -ot rules for GPU placement.
Fix: after loading the assistant from file, rename all tensors not already prefixed with 'mtp.' to 'mtp.<original_name>'. This is done purely in-memory on the tensors_by_name vector and the ggml_tensor name field — the GGUF file and published arch names are unchanged.
After this change, all MTP assistant tensors are addressable as mtp.blk.N.*, mtp.token_embd.weight, mtp.output_norm.weight etc, and can be pinned with:
-ot 'mtp..*=CUDA0'
This leads to speedups on multi GPU systems
This is important on dual GPU systems as splitting MTP head slows down the inference.
Requirements