Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions kubernetes/llama-serve/granite-8b/vllm.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,8 @@ spec:
creationTimestamp: null
labels:
app: granite-8b
annotations:
instrumentation.opentelemetry.io/inject-sdk: "hub" # NOTE: May extend with ".<namespace>"
spec:
containers:
- args:
Expand Down
2 changes: 2 additions & 0 deletions kubernetes/llama-serve/llama3.1-70b/vllm.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@ spec:
creationTimestamp: null
labels:
app: llama31-70b
annotations:
instrumentation.opentelemetry.io/inject-sdk: "hub" # NOTE: May extend with ".<namespace>"
spec:
volumes:
- name: hf-cache
Expand Down
2 changes: 2 additions & 0 deletions kubernetes/llama-serve/llama3.2-3b/vllm.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,8 @@ spec:
creationTimestamp: null
labels:
app: llama32-3b
annotations:
instrumentation.opentelemetry.io/inject-sdk: "hub" # NOTE: May extend with ".<namespace>"
spec:
containers:
- args:
Expand Down
2 changes: 2 additions & 0 deletions kubernetes/llama-serve/watt-8b/vllm.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@ spec:
creationTimestamp: null
labels:
app: watt-8b
annotations:
instrumentation.opentelemetry.io/inject-sdk: "hub" # NOTE: May extend with ".<namespace>"
spec:
volumes:
- name: hf-cache
Expand Down
6 changes: 1 addition & 5 deletions kubernetes/llama-stack/deployment.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ spec:
template:
metadata:
annotations:
sidecar.opentelemetry.io/inject: llamastack-otelsidecar
instrumentation.opentelemetry.io/inject-sdk: "hub" # NOTE: May extend with ".<namespace>"
labels:
app: llamastack
spec:
Expand Down Expand Up @@ -44,10 +44,6 @@ spec:
value: 'https://llama32-3b-llama-serve.apps.ocp-beta-test.nerc.mghpcc.org/v1'
- name: VLLM_API_TOKEN
value: fake
- name: OTEL_SERVICE_NAME
value: om-llamastack
- name: OTEL_TRACE_ENDPOINT
value: 'http://localhost:4318/v1/traces'
- name: SAFETY_MODEL
value: meta-llama/Llama-Guard-3-8B
- name: SAFETY_VLLM_URL
Expand Down
19 changes: 19 additions & 0 deletions kubernetes/observability/otel-sdk-hub-config.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
apiVersion: opentelemetry.io/v1alpha1
kind: Instrumentation
metadata:
name: hub
spec:
exporter:
endpoint: http://otel-collector-collector.observability-hub.svc.cluster.local:4317
env:
# NOTE: can this be provided by the service itself?
# - name: "OTEL_SERVICE_NAME"
# value: "om-llamastack"
- name: "OTEL_EXPORTER_OTLP_TRACES_INSECURE"
value: "true"
# NOTE: Is http requiered?
- name: "OTEL_TRACE_ENDPOINT"
value: "http://otel-collector-collector.observability-hub.svc.cluster.local:4318/v1/traces"
propagators:
- tracecontext
- baggage