phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update more distribution docs to be simpler and partially codegen'ed

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-20 14:44:04 -08:00
parent e84d4436b5
commit 2411a44833
51 changed files with 1188 additions and 291 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/inline/inference/vllm/config.py
View file

@ -37,11 +37,11 @@ class VLLMConfig(BaseModel):
@classmethod
def sample_run_config(cls):
return {
"model": "${env.VLLM_INFERENCE_MODEL:Llama3.2-3B-Instruct}",
"tensor_parallel_size": "${env.VLLM_TENSOR_PARALLEL_SIZE:1}",
"max_tokens": "${env.VLLM_MAX_TOKENS:4096}",
"enforce_eager": "${env.VLLM_ENFORCE_EAGER:False}",
"gpu_memory_utilization": "${env.VLLM_GPU_MEMORY_UTILIZATION:0.3}",
"model": "${env.INFERENCE_MODEL:Llama3.2-3B-Instruct}",
"tensor_parallel_size": "${env.TENSOR_PARALLEL_SIZE:1}",
"max_tokens": "${env.MAX_TOKENS:4096}",
"enforce_eager": "${env.ENFORCE_EAGER:False}",
"gpu_memory_utilization": "${env.GPU_MEMORY_UTILIZATION:0.7}",
}
@field_validator("model")