capture server pid

Author: cquil11

benchmarks/dsr1_fp4_b200_docker.sh

@@ -36,7 +36,6 @@ wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$S
 
 pip install -q datasets pandas
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \

benchmarks/dsr1_fp4_b200_trt_slurm.sh

@@ -108,7 +108,6 @@ source "$(dirname "$0")/benchmark_lib.sh"
 # Wait for server to be ready
 wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \

benchmarks/dsr1_fp4_mi355x_docker.sh

@@ -39,7 +39,6 @@ source "$(dirname "$0")/benchmark_lib.sh"
 # Wait for server to be ready
 wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \

benchmarks/dsr1_fp4_mi355x_slurm.sh

@@ -34,13 +34,14 @@ python3 -m sglang.launch_server --model-path=$MODEL --trust-remote-code \
 --cuda-graph-max-bs=128 \
 > $SERVER_LOG 2>&1 &
 
+SERVER_PID=$!
+
 # Source benchmark utilities
 source "$(dirname "$0")/benchmark_lib.sh"
 
 # Wait for server to be ready
 wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \

benchmarks/dsr1_fp8_b200_docker.sh

@@ -47,7 +47,6 @@ wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$S
 
 pip install -q datasets pandas
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \

benchmarks/dsr1_fp8_b200_trt_slurm.sh

@@ -78,7 +78,6 @@ source "$(dirname "$0")/benchmark_lib.sh"
 # Wait for server to be ready
 wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \

benchmarks/dsr1_fp8_h200_slurm.sh

@@ -52,7 +52,6 @@ source "$(dirname "$0")/benchmark_lib.sh"
 # Wait for server to be ready
 wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \

benchmarks/dsr1_fp8_h200_trt_slurm.sh

@@ -78,7 +78,6 @@ source "$(dirname "$0")/benchmark_lib.sh"
 # Wait for server to be ready
 wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \

benchmarks/dsr1_fp8_mi300x_docker.sh

@@ -37,23 +37,14 @@ python3 -m sglang.launch_server \
 --max-prefill-tokens=196608 \
 --disable-radix-cache > $SERVER_LOG 2>&1 &
 
-
-# Show logs until server is ready
-tail -f $SERVER_LOG &
-TAIL_PID=$!
-set +x
-until curl --output /dev/null --silent --fail http://0.0.0.0:$PORT/health; do
-    sleep 5
-done
-kill $TAIL_PID
+SERVER_PID=$!
 
 # Source benchmark utilities
 source "$(dirname "$0")/benchmark_lib.sh"
 
 # Wait for server to be ready
 wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \

benchmarks/dsr1_fp8_mi300x_slurm.sh

@@ -55,7 +55,6 @@ source "$(dirname "$0")/benchmark_lib.sh"
 # Wait for server to be ready
 wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
 
-set -x
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \