forked from phoenix-oss/llama-stack-mirror
add NVIDIA NIM inference adapter (#355)
# What does this PR do? this PR adds a basic inference adapter to NVIDIA NIMs what it does - - chat completion api - tool calls - streaming - structured output - logprobs - support hosted NIM on integrate.api.nvidia.com - support downloaded NIM containers what it does not do - - completion api - embedding api - vision models - builtin tools - have certainty that sampling strategies are correct ## Feature/Issue validation/testing/test plan `pytest -s -v --providers inference=nvidia llama_stack/providers/tests/inference/ --env NVIDIA_API_KEY=...` all tests should pass. there are pydantic v1 warnings. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [x] Did you write any new necessary tests? Thanks for contributing 🎉!
This commit is contained in:
parent
2cfc41e13b
commit
4e6c984c26
10 changed files with 934 additions and 10 deletions
|
@ -29,7 +29,6 @@ def build_model_alias(provider_model_id: str, model_descriptor: str) -> ModelAli
|
|||
return ModelAlias(
|
||||
provider_model_id=provider_model_id,
|
||||
aliases=[
|
||||
model_descriptor,
|
||||
get_huggingface_repo(model_descriptor),
|
||||
],
|
||||
llama_model=model_descriptor,
|
||||
|
@ -57,6 +56,10 @@ class ModelRegistryHelper(ModelsProtocolPrivate):
|
|||
self.alias_to_provider_id_map[alias_obj.provider_model_id] = (
|
||||
alias_obj.provider_model_id
|
||||
)
|
||||
# ensure we can go from llama model to provider model id
|
||||
self.alias_to_provider_id_map[alias_obj.llama_model] = (
|
||||
alias_obj.provider_model_id
|
||||
)
|
||||
self.provider_id_to_llama_model_map[alias_obj.provider_model_id] = (
|
||||
alias_obj.llama_model
|
||||
)
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue