[docs] Eagle3 qwen3 draft model support#24977
Merged
Merged
Conversation
github-actions
Bot
added
documentation
Member
|
cc/ @ruixiang63 Review please. :) |
ruixiang63
reviewed
Jun 25, 2026
ruixiang63
left a comment
ruixiang63
left a comment
Member
There was a problem hiding this comment.
Thanks for updating this! I left some comments and overall looks good to me.
Please also add eagle3 in --spec-type section: https://github.com/kashif/llama.cpp/blob/5e579af58657e73aa44d484168da5fa2b492fe62/docs/speculative.md#--spec-type-type
ruixiang63
reviewed
Jun 25, 2026
Member
|
LGTM. cc @CISC |
ruixiang63
approved these changes
Jun 25, 2026
CISC
approved these changes
Jun 25, 2026
CISC
added
the
merge ready
papamoose
pushed a commit
to papamoose/llama.cpp
that referenced
this pull request
Jun 27, 2026
* eagle3: accept Eagle3LlamaForCausalLM draft checkpoints * docs: add eagle3 speculative decoding section * docs: address eagle3 review comments * docs: add more angelslim eagle3 models * docs: add gpt-oss eagle3 models and link to pr 18039
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This pull request adds support for the EAGLE-3 draft model format in the speculative decoding system. The changes include updating model mappings, import lists, and documentation to describe how to use EAGLE-3 as a draft model for speculative decoding.
Support for EAGLE-3 draft models:
"Eagle3LlamaForCausalLM"to the model type mapping inconversion/__init__.pyto recognize EAGLE-3 draft models as Llama-based."Eagle3LlamaForCausalLM"in the import list of supported models inconversion/llama.py.Documentation updates:
docs/speculative.mddescribing EAGLE-3 draft model usage, conversion steps, and compatibility with existing formats.docs/speculative.mdto includedraft-eagle3as a valid--spec-typeoption.Additional information
Requirements