Unverified Commit 036eb4fe authored by ishandhanani's avatar ishandhanani Committed by GitHub
Browse files

fix(sglang): remove otel for emebedding models (#5100)

parent 7053bb25
...@@ -12,20 +12,15 @@ cleanup() { ...@@ -12,20 +12,15 @@ cleanup() {
trap cleanup EXIT INT TERM trap cleanup EXIT INT TERM
# Parse command line arguments # Parse command line arguments
ENABLE_OTEL=false
while [[ $# -gt 0 ]]; do while [[ $# -gt 0 ]]; do
case $1 in case $1 in
--enable-otel)
ENABLE_OTEL=true
shift
;;
-h|--help) -h|--help)
echo "Usage: $0 [OPTIONS]" echo "Usage: $0 [OPTIONS]"
echo "Options:" echo "Options:"
echo " --enable-otel Enable OpenTelemetry tracing"
echo " -h, --help Show this help message" echo " -h, --help Show this help message"
echo "" echo ""
echo "Note: System metrics are enabled by default on port 8081 (worker)" echo "Note: System metrics are enabled by default on port 8081 (worker)"
echo "Note: OpenTelemetry tracing is not yet supported for embedding models"
exit 0 exit 0
;; ;;
*) *)
...@@ -36,23 +31,13 @@ while [[ $# -gt 0 ]]; do ...@@ -36,23 +31,13 @@ while [[ $# -gt 0 ]]; do
esac esac
done done
# Enable tracing if requested
TRACE_ARGS=()
if [ "$ENABLE_OTEL" = true ]; then
export DYN_LOGGING_JSONL=true
export OTEL_EXPORT_ENABLED=1
export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=${OTEL_EXPORTER_OTLP_TRACES_ENDPOINT:-http://localhost:4317}
TRACE_ARGS+=(--enable-trace --otlp-traces-endpoint localhost:4317)
fi
# run ingress # run ingress
# dynamo.frontend accepts either --http-port flag or DYN_HTTP_PORT env var (defaults to 8000) # dynamo.frontend accepts either --http-port flag or DYN_HTTP_PORT env var (defaults to 8000)
OTEL_SERVICE_NAME=dynamo-frontend \
python3 -m dynamo.frontend & python3 -m dynamo.frontend &
DYNAMO_PID=$! DYNAMO_PID=$!
# run worker # run worker
OTEL_SERVICE_NAME=dynamo-worker-embedding DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT:-8081} \ DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT:-8081} \
python3 -m dynamo.sglang \ python3 -m dynamo.sglang \
--embedding-worker \ --embedding-worker \
--model-path Qwen/Qwen3-Embedding-4B \ --model-path Qwen/Qwen3-Embedding-4B \
...@@ -61,5 +46,4 @@ python3 -m dynamo.sglang \ ...@@ -61,5 +46,4 @@ python3 -m dynamo.sglang \
--tp 1 \ --tp 1 \
--trust-remote-code \ --trust-remote-code \
--use-sglang-tokenizer \ --use-sglang-tokenizer \
--enable-metrics \ --enable-metrics
"${TRACE_ARGS[@]}"
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment