phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Significantly simpler and malleable test setup (#360)

Browse source 
* Significantly simpler and malleable test setup

* convert memory tests

* refactor fixtures and add support for composable fixtures

* Fix memory to use the newer fixture organization

* Get agents tests working

* Safety tests work

* yet another refactor to make this more general

now it accepts --inference-model, --safety-model options also

* get multiple providers working for meta-reference (for inference + safety)

* Add README.md

---------

Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
This commit is contained in:
Ashwin Bharambe 2024-11-04 17:36:43 -08:00 • committed by GitHub
parent 663883cc29
commit ffedb81c11
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
25 changed files with 1491 additions and 790 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/adapters/inference/together/together.py
View file

@ -38,13 +38,14 @@ TOGETHER_SUPPORTED_MODELS = {
"Llama3.2-3B-Instruct": "meta-llama/Llama-3.2-3B-Instruct-Turbo",
"Llama3.2-11B-Vision-Instruct": "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
"Llama3.2-90B-Vision-Instruct": "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
"Llama-Guard-3-8B": "meta-llama/Meta-Llama-Guard-3-8B",
"Llama-Guard-3-11B-Vision": "meta-llama/Llama-Guard-3-11B-Vision-Turbo",
}
class TogetherInferenceAdapter(
ModelRegistryHelper, Inference, NeedsRequestProviderData
):
def __init__(self, config: TogetherImplConfig) -> None:
ModelRegistryHelper.__init__(
self, stack_to_provider_models_map=TOGETHER_SUPPORTED_MODELS
@ -150,7 +151,6 @@ class TogetherInferenceAdapter(
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
request = ChatCompletionRequest(
model=model,
messages=messages,