phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-29 22:59:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-watsonx-inference-adapter

Browse source
This commit is contained in:
Sajikumar JS 2025-04-17 10:43:38 +05:30
commit 34a3f1a749
12 changed files with 237 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -374,7 +374,8 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
options["max_tokens"] = self.config.max_tokens
input_dict: dict[str, Any] = {}
if isinstance(request, ChatCompletionRequest) and request.tools is not None:
# Only include the 'tools' param if there is any. It can break things if an empty list is sent to the vLLM.
if isinstance(request, ChatCompletionRequest) and request.tools:
input_dict = {"tools": _convert_to_vllm_tools_in_request(request.tools)}
if isinstance(request, ChatCompletionRequest):

6
llama_stack/providers/remote/post_training/nvidia/models.py
View file

@ -16,7 +16,11 @@ _MODEL_ENTRIES = [
build_hf_repo_model_entry(
"meta/llama-3.1-8b-instruct",
CoreModelId.llama3_1_8b_instruct.value,
)
),
build_hf_repo_model_entry(
"meta/llama-3.2-1b-instruct",
CoreModelId.llama3_2_1b_instruct.value,
),
]