phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 21:39:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

more progress on auto-generation

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-15 09:35:38 -08:00
parent cfa913fdd5
commit e4509cb568
10 changed files with 309 additions and 73 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -35,7 +35,7 @@ class VLLMConfig(BaseModel):
)
@classmethod
def sample_dict(cls):
def sample_run_config(cls):
return {
"model": "${env.VLLM_INFERENCE_MODEL:Llama3.2-3B-Instruct}",
"tensor_parallel_size": "${env.VLLM_TENSOR_PARALLEL_SIZE:1}",