mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
36822fa49c
* remove splitwise deployment on single node and refine the code * up * up * up * add test * up
112 lines
2.9 KiB
Bash
112 lines
2.9 KiB
Bash
#!/bin/bash
|
|
set -e
|
|
|
|
# Test splitwise deployment
|
|
# There are two methods for splitwise deployment:
|
|
# v0: using splitwise_scheduler or dp_scheduler
|
|
# v1: using local_scheduler + router
|
|
|
|
wait_for_health() {
|
|
local server_port=$1
|
|
while true; do
|
|
status_code=$(curl -s -o /dev/null -w "%{http_code}" "http://0.0.0.0:${server_port}/health" || echo "000")
|
|
if [ "$status_code" -eq 200 ]; then
|
|
break
|
|
else
|
|
echo "Service not ready. Retrying in 2s..."
|
|
sleep 2
|
|
fi
|
|
done
|
|
}
|
|
|
|
# prepare environment
|
|
MODEL_NAME="PaddlePaddle/ERNIE-4.5-0.3B-Paddle"
|
|
|
|
export FD_DEBUG=1
|
|
export ENABLE_V1_KVCACHE_SCHEDULER=0
|
|
export KVCACHE_GDRCOPY_FLUSH_ENABLE=1
|
|
|
|
SCRIPT_PATH=$(readlink -f "$0")
|
|
SCRIPT_DIR=$(dirname "$SCRIPT_PATH")
|
|
export $(bash ${SCRIPT_DIR}/../../scripts/get_rdma_nics.sh gpu)
|
|
echo "KVCACHE_RDMA_NICS:${KVCACHE_RDMA_NICS}"
|
|
if [ -z "${KVCACHE_RDMA_NICS}" ]; then
|
|
echo "KVCACHE_RDMA_NICS is empty, please check the output of get_rdma_nics.sh"
|
|
exit 1
|
|
fi
|
|
|
|
unset http_proxy && unset https_proxy
|
|
rm -rf log_*
|
|
|
|
# start redis
|
|
if ! redis-cli ping &>/dev/null; then
|
|
echo "Redis is not running. Starting redis-server..."
|
|
redis-server --daemonize yes
|
|
sleep 1
|
|
else
|
|
echo "Redis is already running."
|
|
fi
|
|
sleep 1
|
|
|
|
# start prefill
|
|
export CUDA_VISIBLE_DEVICES=0,1
|
|
export FD_LOG_DIR="log_prefill"
|
|
mkdir -p ${FD_LOG_DIR}
|
|
|
|
nohup python -m fastdeploy.entrypoints.openai.api_server \
|
|
--model ${MODEL_NAME} \
|
|
--port 8100 \
|
|
--metrics-port 8101 \
|
|
--engine-worker-queue-port 8102 \
|
|
--cache-queue-port 8103 \
|
|
--max-model-len 32768 \
|
|
--tensor-parallel-size 2 \
|
|
--splitwise-role "prefill" \
|
|
--cache-transfer-protocol "rdma,ipc" \
|
|
--pd-comm-port 8104 \
|
|
--rdma-comm-ports 8105,8106 \
|
|
--scheduler-name "splitwise" \
|
|
--scheduler-host "127.0.0.1" \
|
|
--scheduler-port 6379 \
|
|
--scheduler-ttl 9000 \
|
|
2>&1 >${FD_LOG_DIR}/nohup &
|
|
# wait_for_health 8100
|
|
|
|
# start decode
|
|
export CUDA_VISIBLE_DEVICES=2,3
|
|
export FD_LOG_DIR="log_decode"
|
|
mkdir -p ${FD_LOG_DIR}
|
|
|
|
nohup python -m fastdeploy.entrypoints.openai.api_server \
|
|
--model ${MODEL_NAME} \
|
|
--port 9000 \
|
|
--metrics-port 9001 \
|
|
--engine-worker-queue-port 9002 \
|
|
--cache-queue-port 9003 \
|
|
--max-model-len 32768 \
|
|
--tensor-parallel-size 2 \
|
|
--splitwise-role "decode" \
|
|
--cache-transfer-protocol "rdma,ipc" \
|
|
--pd-comm-port 9004 \
|
|
--rdma-comm-ports 9005,9006 \
|
|
--scheduler-name "splitwise" \
|
|
--scheduler-host "127.0.0.1" \
|
|
--scheduler-port 6379 \
|
|
--scheduler-ttl 9000 \
|
|
2>&1 >${FD_LOG_DIR}/nohup &
|
|
wait_for_health 9000
|
|
|
|
|
|
# send request
|
|
sleep 10 # make sure server is registered to router
|
|
port=9000
|
|
curl -X POST "http://0.0.0.0:${port}/v1/chat/completions" \
|
|
-H "Content-Type: application/json" \
|
|
-d '{
|
|
"messages": [
|
|
{"role": "user", "content": "hello"}
|
|
],
|
|
"max_tokens": 20,
|
|
"stream": true
|
|
}'
|