phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 20:12:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge origin/main into add-missing-provider-data-impls

Browse source 
Resolved conflicts in:
- benchmarking/k8s-benchmark/stack_run_config.yaml (accepted new storage schema)
- llama_stack/providers/remote/inference/cerebras/cerebras.py (kept provider data support)
- llama_stack/providers/remote/inference/cerebras/config.py (kept provider data support)
- llama_stack/providers/remote/inference/nvidia/config.py (kept provider data support)
- llama_stack/providers/remote/inference/runpod/config.py (merged imports)
- pyproject.toml (kept databricks-sdk dependency)
This commit is contained in:
Ashwin Bharambe 2025-10-27 11:39:00 -07:00
commit 9eb9a37ee4
1880 changed files with 804868 additions and 70533 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/registry/inference.py
View file

@ -43,6 +43,12 @@ def available_providers() -> list[ProviderSpec]:
pip_packages=[
"torch torchvision torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu",
"sentence-transformers --no-deps",
# required by some SentenceTransformers architectures for tensor rearrange/merge ops
"einops",
# fast HF tokenization backend used by SentenceTransformers models
"tokenizers",
# safe and fast file format for storing and loading tensors
"safetensors",
],
module="llama_stack.providers.inline.inference.sentence_transformers",
config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
@ -275,7 +281,7 @@ Available Models:
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.watsonx",
config_class="llama_stack.providers.remote.inference.watsonx.WatsonXConfig",
provider_data_validator="llama_stack.providers.remote.inference.watsonx.WatsonXProviderDataValidator",
provider_data_validator="llama_stack.providers.remote.inference.watsonx.config.WatsonXProviderDataValidator",
description="IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform.",
),
RemoteProviderSpec(