Skip to content
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.

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

Error in building llama with eagle for speculative decoding #2588

Open
JoJoLev opened this issue Dec 18, 2024 · 4 comments
Open

Error in building llama with eagle for speculative decoding #2588

JoJoLev opened this issue Dec 18, 2024 · 4 comments
Assignees
Labels
Investigating Speculative Decoding triaged Issue has been triaged by maintainers

Comments

@JoJoLev
Copy link

JoJoLev commented Dec 18, 2024

Went through the Readme for llama 3 8b instruct on the examples/eagle. When running the convert checkpoint, I get the error: key error 'fc.bias'

I used llama3 8b instruct from hugging face with the eagle version for the eagle model directory.

Not really sure the issue? Maybe I need to recreate the eagle model?

@nv-guomingz
Copy link
Collaborator

Hi @JoJoLev Sorry, examples/eagle doesn't mention llama3 8b. Do we miss something?

@JoJoLev
Copy link
Author

JoJoLev commented Dec 18, 2024

@nv-guomingz hello there, thanks for the quick reply! 😀

No, I don't see anything specifically calling out models? I was under the impression that those models built and in the HF repo for Eagle should work here for a quick demo/check.
Per the docs:

Limitations

EAGLE-2 is not supported.
All EAGLE choices have to have exactly the same depth as num_eagle_layers of the engine.
Pipeline parallelism is not supported.

I didn't see any other limitations listed.

Here is the HF model I listed for the eagle directory: https://huggingface.co/yuhuili/EAGLE-LLaMA3-Instruct-8B

I then added the base llama3 instruction as the model directory.

Is there a place where specific model support is called out?

@nv-guomingz
Copy link
Collaborator

Hi @JoJoLev vicuna-7b-v1.3 is a verified example model for Eagle feature, I think the team didn't verify the models u mentioned above.
So the failure is very possible but I consider it as a corner case.
Let's have a try and get back to you ASAP.

@nv-guomingz
Copy link
Collaborator

Hi @nekorobov would u please take a look this issue?

@nv-guomingz nv-guomingz added Speculative Decoding triaged Issue has been triaged by maintainers labels Dec 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Investigating Speculative Decoding triaged Issue has been triaged by maintainers
Projects
None yet
Development

No branches or pull requests

3 participants