phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 04:50:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update llama_stack/providers/inline/inference/vllm/vllm.py

Browse source 
Co-authored-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Fred Reiss 2025-02-15 17:13:10 -08:00 • committed by Ashwin Bharambe
parent 33c65ad86b
commit 258d4c0b0f
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -263,7 +263,7 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
# Load from Hugging Face repo into default local cache dir # Load from Hugging Face repo into default local cache dir
resolved_model_id = resolved_llama_model.huggingface_repo resolved_model_id = resolved_llama_model.huggingface_repo
# Detect a geniune Meta Llama model to trigger Meta-specific preprocessing. # Detect a genuine Meta Llama model to trigger Meta-specific preprocessing.
# Don't set self.is_meta_llama_model until we actually load the model. # Don't set self.is_meta_llama_model until we actually load the model.
is_meta_llama_model = True is_meta_llama_model = True
else: # if resolved_llama_model is None else: # if resolved_llama_model is None