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.

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

Jump to bottom

add nvidia distribution #565

Merged
merged 19 commits into from
Jan 15, 2025
Merged

add nvidia distribution #565

merged 19 commits into from
Jan 15, 2025

Conversation

cdgamarose-nv
Copy link
Contributor

@cdgamarose-nv cdgamarose-nv commented Dec 4, 2024 •
edited
Loading

What does this PR do?

adds nvidia template for creating a distribution using inference adapter for NVIDIA NIMs.

Test Plan

Please describe:
Build llama stack distribution for nvidia using the template, docker and conda.

(.venv) local-cdgamarose@a4u8g-0006:~/llama-stack$ llama-stack-client configure --endpoint http://localhost:5000
Done! You can now use the Llama Stack Client CLI with endpoint http://localhost:5000
(.venv) local-cdgamarose@a4u8g-0006:~/llama-stack$ llama-stack-client models list
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ identifier                       ┃ provider_id ┃ provider_resource_id       ┃ metadata ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
│ Llama3.1-8B-Instruct             │ nvidia      │ meta/llama-3.1-8b-instruct │ {}       │
│ meta-llama/Llama-3.2-3B-Instruct │ nvidia      │ meta/llama-3.2-3b-instruct │ {}       │
└──────────────────────────────────┴─────────────┴────────────────────────────┴──────────┘
(.venv) local-cdgamarose@a4u8g-0006:~/llama-stack$ llama-stack-client inference chat-completion --message "hello, write me a 2 sentence poem"
ChatCompletionResponse(
    completion_message=CompletionMessage(
        content='Here is a 2 sentence poem:\n\nThe sun sets slow and paints the sky, \nA gentle hue of pink that makes me sigh.',
        role='assistant',
        stop_reason='end_of_turn',
        tool_calls=[]
    ),
    logprobs=None
)

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Ran pre-commit to handle lint / formatting issues.
  • Read the contributor guideline,
    Pull Request section?
  • Updated relevant documentation.
  • Wrote necessary unit or integration tests.

mattf and others added 15 commits November 4, 2024 10:23
@mattf
add NVIDIA NIM inference adapter
2dd8c4b
@mattf
enable streaming support, use openai-python instead of httpx
dbe665e
@mattf
Merge branch 'main' into add-nvidia-inference-adapter
43262df
@mattf
Merge branch 'main' into add-nvidia-inference-adapter
c24f882
@mattf
Merge branch 'main' into add-nvidia-inference-adapter
2a25ace
@mattf
map llama model -> provider model id in ModelRegistryHelper
2980a18
@cdgamarose-nv
Merge remote-tracking branch 'mattf/add-nvidia-inference-adapter' int…
18e8f18 
…o cdgamarose/add_nvidia_distro

merging matt's changes
@cdgamarose-nv
Add nvidia remote distro
a5d4130
@mattf
align with other remote adapters, rename config base_url -> url
4ccf4ef
@mattf
Merge branch 'main' into add-nvidia-inference-adapter
8a35dc8
@cdgamarose-nv
Added distributions for inline and remote
6759744
@cdgamarose-nv
Merge remote-tracking branch 'mattf/add-nvidia-inference-adapter' int…
3b5ea74 
…o cdgamarose/add_nvidia_distro
@cdgamarose-nv
Merge conflicts
5b027d2
@cdgamarose-nv
Reverted outdated changes
deecc27
@cdgamarose-nv
Changing fireworks to nvidia in docs
091d196
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Meta Open Source bot. label Dec 4, 2024
@cdgamarose-nv
Copy link
Contributor Author

@mattf for viz

@cdgamarose-nv cdgamarose-nv marked this pull request as draft December 4, 2024 03:30
@mattf mattf mentioned this pull request Dec 4, 2024
Merged
5 tasks
@cdgamarose-nv cdgamarose-nv marked this pull request as ready for review January 10, 2025 22:02
@cdgamarose-nv
Copy link
Contributor Author

I used a dev docker image to test this (distribution-nvidia:dev). Do we push the image to dockerhub, or there a process to follow?

@ashwinb
Copy link
Contributor

ashwinb commented Jan 14, 2025

@cdgamarose-nv yeah we are setting up CI for automatically uploading dockers when we make them for the supported distributions. Pretty imminent!

ashwinb
ashwinb reviewed Jan 14, 2025
View reviewed changes
distributions/inline-nvidia/run.yaml
@@ -0,0 +1,100 @@
version: '2'
Copy link
Contributor

Choose a reason for hiding this comment

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

I don't think you need an inline-nvidia distro at all?

ashwinb
ashwinb requested changes Jan 14, 2025
View reviewed changes
Copy link
Contributor

@ashwinb ashwinb left a comment

Choose a reason for hiding this comment

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

need to remove inline-nvidia

@yanxi0830
Copy link
Contributor

I used a dev docker image to test this (distribution-nvidia:dev). Do we push the image to dockerhub, or there a process to follow?

@cdgamarose-nv yes! we have just added a Github workflow to build docker images and update to dockerhub: https://github.com/meta-llama/llama-stack/actions/workflows/publish-to-docker.yml

@yanxi0830
Copy link
Contributor

yanxi0830 commented Jan 15, 2025 •
edited
Loading

Merging this PR in and rebasing on top to remove inline-nvidia template as offline synced with @ashwinb.

@yanxi0830 yanxi0830 merged commit b3202bc into meta-llama:main Jan 15, 2025
2 checks passed
@yanxi0830
Copy link
Contributor

Removed inline-nvidia template in 27e07b4

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ashwinb ashwinb ashwinb requested changes

@yanxi0830 yanxi0830 yanxi0830 approved these changes

@hardikjshah hardikjshah Awaiting requested review from hardikjshah hardikjshah is a code owner

@dltn dltn Awaiting requested review from dltn dltn is a code owner

@raghotham raghotham Awaiting requested review from raghotham raghotham is a code owner

@dineshyv dineshyv Awaiting requested review from dineshyv dineshyv is a code owner

@vladimirivic vladimirivic Awaiting requested review from vladimirivic vladimirivic is a code owner

@sixianyi0721 sixianyi0721 Awaiting requested review from sixianyi0721 sixianyi0721 is a code owner

Assignees
No one assigned
Labels
CLA Signed This label is managed by the Meta Open Source bot.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@cdgamarose-nv @ashwinb @yanxi0830 @facebook-github-bot @mattf