Skip to content

spec : auto-detect mtp draft model type #27005

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ngxson merged 1 commit into from
Aug 13, 2026
Merged

spec : auto-detect mtp draft model type #27005

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions common/speculative.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2246,6 +2246,12 @@ std::vector<common_speculative_type> common_speculative_types_from_gguf(const st

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()));

@ngxson ngxson Aug 13, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should we throw error if gguf_find_key fails ?

@CISC CISC Aug 13, 2026

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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.


if (gguf_find_tensor(gguf_ctx.get(), ("blk." + std::to_string(block_count - 1) + ".nextn.eh_proj.weight").c_str()) >= 0) {
return { COMMON_SPECULATIVE_TYPE_DRAFT_MTP };
}

return {};
}

Expand Down
Loading