Use Case: Enhancing LLM Serving with Torch Compiled RAG on AWS Graviton #3276
Conversation
This file contains 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
mreso
approved these changes
Aug 2, 2024
|
|
||
| ### Download Llama | ||
|
|
||
| Follow [this instruction](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) to get permission |
There was a problem hiding this comment.
Would be good to update this to Llama 3.1 now that its released https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct
There was a problem hiding this comment.
I tried 3.1. One interesting observation was , when I ask it "What's new with Llama 3.1", it gives an acceptable answer, which shouldn't be possible. :D
So, for this usecase Llama 3 drives home the point better
|
|
||
| ### Download Llama | ||
|
|
||
| Follow [this instruction](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) to get permission |
There was a problem hiding this comment.
Suggested change
| Follow [this instruction](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) to get permission | |
| Follow [this instruction](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) to get permission |
| huggingface-cli login --token $HUGGINGFACE_TOKEN | ||
|
|
||
| ```bash | ||
| python ../Download_model.py --model_path model --model_name meta-llama/Meta-Llama-3-8B-Instruct |
There was a problem hiding this comment.
Suggested change
| python ../Download_model.py --model_path model --model_name meta-llama/Meta-Llama-3-8B-Instruct | |
| python ../Download_model.py --model_path model --model_name meta-llama/Meta-Llama-3.1-8B-Instruct |
| ```bash | ||
| python ../Download_model.py --model_path model --model_name meta-llama/Meta-Llama-3-8B-Instruct | ||
| ``` | ||
| Model will be saved in the following path, `model/models--meta-llama--Meta-Llama-3-8B-Instruct`. |
There was a problem hiding this comment.
Suggested change
| Model will be saved in the following path, `model/models--meta-llama--Meta-Llama-3-8B-Instruct`. | |
| Model will be saved in the following path, `model/models--meta-llama--Meta-Llama-3.1-8B-Instruct`. |
Co-authored-by: Matthias Reso <13337103+mreso@users.noreply.github.com>
Co-authored-by: Matthias Reso <13337103+mreso@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Description
This PR shows a use case of TorchServe for GenAI deployment.
The use-case shows how torch.compile can be used on embedding model in RAG to improve throughput and how this RAG endpoint can be used along with an LLM endpoint to improve results from the LLM
Fixes #(issue)
Type of change
Please delete options that are not relevant.
Feature/Issue validation/testing
Please describe the Unit or Integration tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.
Test A
Logs for Test A
Test B
Logs for Test B
Checklist: