apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 21 Packages Projects Releases Wiki Activity

[CI] Refactor RL tests to reuse stable_test (#5516)

Browse Source 
* [CI] Refactor RL tests to reuse stable_test
This commit is contained in:
YuBaoku
2025-12-24 19:18:00 +08:00
committed by GitHub
parent 2dc2ba49b5
commit 0410c42a9a
3 changed files with 24 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/ce/stable_cases/launch_model.sh
+4 -5
View File
@@ -1,9 +1,9 @@
#!/bin/bash
MODEL_PATH="${1}/TP2"
FD_API_PORT=${FD_API_PORT:-8000}
FD_ENGINE_QUEUE_PORT=${FD_ENGINE_QUEUE_PORT:-8001}
FD_METRICS_PORT=${FD_METRICS_PORT:-8002}
FD_CACHE_QUEUE_PORT=${FD_CACHE_QUEUE_PORT:-8003}
FD_API_PORT=${FD_API_PORT:-8180}
FD_ENGINE_QUEUE_PORT=${FD_ENGINE_QUEUE_PORT:-8181}
FD_METRICS_PORT=${FD_METRICS_PORT:-8182}
FD_CACHE_QUEUE_PORT=${FD_CACHE_QUEUE_PORT:-8183}
@@ -36,7 +36,6 @@ python -m fastdeploy.entrypoints.openai.api_server \
--engine-worker-queue-port ${FD_ENGINE_QUEUE_PORT} \
--metrics-port ${FD_METRICS_PORT} \
--cache-queue-port ${FD_CACHE_QUEUE_PORT} \
--quantization wint8 \
--max-model-len 32768 \
--max-num-seqs 1 \
--gpu-memory-utilization 0.9 \