This commit is contained in:
Kai Wu 2025-08-05 13:33:32 -07:00
parent 62c758932d
commit f02fda0bd7
12 changed files with 5521 additions and 14 deletions

View file

@ -75,6 +75,10 @@ spec:
value: http://vllm-server.default.svc.cluster.local:8001/v1
- name: VLLM_MAX_TOKENS
value: "3072"
- name: OTEL_EXPORTER_OTLP_ENDPOINT
value: http://jaeger-dev-collector.observability:4318
- name: OTEL_SERVICE_NAME
value: llama-stack
- name: NVIDIA_BASE_URL
value: http://llm-nim-code.default.svc.cluster.local:8000
- name: OLLAMA_BASE_URL