spec : auto-detect mtp draft model type - #27005
Merged
Merged
Conversation
CISC
changed the title
ngxson
approved these changes
Aug 13, 2026
ngxson
reviewed
Aug 13, 2026
|
|
||
| const std::string arch = gguf_get_val_str(gguf_ctx.get(), arch_id); | ||
| if (arch != "dflash") { | ||
| const uint32_t block_count = gguf_get_val_u32(gguf_ctx.get(), gguf_find_key(gguf_ctx.get(), (arch + ".block_count").c_str())); |
Collaborator
There was a problem hiding this comment.
should we throw error if gguf_find_key fails ?
Member
Author
There was a problem hiding this comment.
It will return -1 which will GGML_ASSERT in gguf_get_val_u32, and since <arch>.block_count is a required key I don't think we need to be very informative here.
EZForever
added a commit
to EZForever/llama.cpp
that referenced
this pull request
Aug 14, 2026
ngxson
added a commit
that referenced
this pull request
Aug 15, 2026
* common: support --models-dir loading MTP assistant models * common: preset: check for MTP models with strict prefix * common: preset: Take advantage of PR #27005 * handle other draft types * drop eagle3 * clean up --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
CowboyTim
pushed a commit
to aardbeiplantje/llama.cpp
that referenced
this pull request
Aug 16, 2026
CowboyTim
pushed a commit
to aardbeiplantje/llama.cpp
that referenced
this pull request
Aug 16, 2026
…4431) * common: support --models-dir loading MTP assistant models * common: preset: check for MTP models with strict prefix * common: preset: Take advantage of PR ggml-org#27005 * handle other draft types * drop eagle3 * clean up --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
brittlewis12
pushed a commit
to brittlewis12/llama.cpp
that referenced
this pull request
Aug 17, 2026
brittlewis12
pushed a commit
to brittlewis12/llama.cpp
that referenced
this pull request
Aug 17, 2026
…4431) * common: support --models-dir loading MTP assistant models * common: preset: check for MTP models with strict prefix * common: preset: Take advantage of PR ggml-org#27005 * handle other draft types * drop eagle3 * clean up --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
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
cont #26814
Additional information
Checks for presence of NextN tensor in draft model to auto-detect
draft-mtp.Requirements