Open paolovic opened 1 month ago
I even get this error in my logs
2024-08-30 14:23:04,700 WARNING runtime_env_agent.py:322 -- runtime_env field CUDA_VISIBLE_DEVICES is not recognized by Ray and will be ignored. In the future, unrecognized fields in the runtime_env will raise an exception.
What happened + What you expected to happen
Hi,
I have a
deployments.yaml
configured that looks like thisIt calls the
depl
class insidevllm_inf.vllm_serve.py
When I log out
os.environ["CUDA_VISIBLE_DEVICES"]
inside that class, it is empty.But instead, it should return "0,1", correct?
What am I doing wrong? I am using Ray together with vllm, and vllm fails now because of the empty
CUDA_VISIBLE_DEVICES
I am serving ray like the followingVersions / Dependencies
ray[train,serve,tune,data]==2.34.0 python==3.11.9 vllm==0.5.5
Reproduction script
vllm_inf.vllm_serve.py
@serve.deployment(name="vLLMGenericAPI") @serve.ingress(app) class VLLMGenerateDeployment: def init(self, default_max_tokens: int, **kwargs): """ logger.info(f"CUDA_VISIBLE_DEVICES: {os.environ['CUDA_VISIBLE_DEVICES']}")
def depl(args: Dict[str, str]) -> Application: return VLLMGenerateDeployment.bind(**args)
Issue Severity
None