41 lines
1.3 KiB
YAML
41 lines
1.3 KiB
YAML
|
# Stable client-facing name for the coder chat model, deliberately decoupled
|
||
|
|
# from the process that serves it.
|
||
|
|
#
|
||
|
|
# poimen-memory addresses a Service, not a pod and not an InferenceService. The
|
||
|
|
# vLLM -> candle-vllm handoff therefore changes this file's selector and nothing
|
||
|
|
# else, so the client config never changes again and there is no window in which
|
||
|
|
# the host name is wrong.
|
||
|
|
#
|
||
|
|
# The previous KTML predictor requested two V100s and never reached Ready, so it
|
||
|
|
# held half the GPU pool while serving nothing. candle-vllm replaces it.
|
||
|
|
#
|
||
|
|
# Two ports on purpose:
|
||
|
|
# - 80 matches every other predictor Service in this namespace, and matches
|
||
|
|
# a client base URL that carries no port number.
|
||
|
|
# - 8080 is the container port. Publishing it directly avoids a port
|
||
|
|
# translation that is easy to get wrong in a curl.
|
||
|
|
#
|
||
|
|
# Do not delete and recreate this Service: a delete drops the ClusterIP, and a
|
||
|
|
# client that cached the name during the gap fails until it re-resolves.
|
||
|
|
apiVersion: v1
|
||
|
|
kind: Service
|
||
|
|
metadata:
|
||
|
|
name: coder-predictor
|
||
|
|
namespace: llm-serving
|
||
|
|
labels:
|
||
|
|
app.kubernetes.io/part-of: llm-serving
|
||
|
|
app: coder-predictor
|
||
|
|
spec:
|
||
|
|
type: ClusterIP
|
||
|
|
selector:
|
||
|
|
app: candle-vllm
|
||
|
|
ports:
|
||
|
|
- name: http
|
||
|
|
protocol: TCP
|
||
|
|
port: 80
|
||
|
|
targetPort: 8080
|
||
|
|
- name: http-8080
|
||
|
|
protocol: TCP
|
||
|
|
port: 8080
|
||
|
|
targetPort: 8080
|