apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

xpu (#4969)

Browse Source
This commit is contained in:
bukejiyu
2025-11-12 15:12:59 +08:00
committed by GitHub
parent 5bf48de999
commit 6e2e2fcd29
4 changed files with 13 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
scripts/run_ci_xpu.sh
View File

@@ -81,8 +81,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--num-gpu-blocks-override 16384 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization wint4 \
--load-choices default > server.log 2>&1 &
--quantization wint4 > server.log 2>&1 &
sleep 60
# 探活
@@ -157,8 +156,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--num-gpu-blocks-override 16384 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "W4A8" \
--load-choices default > server.log 2>&1 &
--quantization "W4A8" > server.log 2>&1 &
sleep 60
# 探活
@@ -236,8 +234,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
--reasoning-parser ernie-45-vl \
--load-choices default > server.log 2>&1 &
--reasoning-parser ernie-45-vl > server.log 2>&1 &
sleep 60
# 探活