docs: exporting a draft model from a quantized model.#1455
Open
rauletorresc wants to merge 3 commits into
Open
docs: exporting a draft model from a quantized model.#1455rauletorresc wants to merge 3 commits into
rauletorresc wants to merge 3 commits into
Conversation
MTP documentation assumes the base model is not quantized. Unfortunately, if we extract a draft model from a quantized model, the resulting draft model will not be quantized by default. This PR details the necessary steps for quantizing a draft model for correct speculative decoding serving.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the MTP documentation to include a comprehensive guide on exporting draft models from quantized base models, including necessary scripts and configuration patches. The reviewer provided feedback to improve the robustness and portability of the documentation's scripts by recommending the removal of hardcoded paths and the use of standard working directories instead of /root/.
liutongxuan
changed the title
Contributor
Author
|
Hi @liutongxuan could you please review this PR again? |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
MTP documentation assumes the base model is not quantized. Unfortunately, if we extract a draft model from a quantized model, the resulting draft model will not be quantized by default. This PR details the necessary steps for quantizing a draft model for correct speculative decoding serving.