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 19 Packages Projects Releases Wiki Activity

[Cherry-Pick][BugFix] cp fix_cpu_cache_bugs(#5544) (#5577)

Browse Source 
* cp fix_cpu_cache_bugs

* update ce case

* update test case

* update code
This commit is contained in:
kevin
2025-12-19 11:48:50 +08:00
committed by GitHub
parent 2aa88d3621
commit 23bfd28624
8 changed files with 14 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/_base_test.yml
+1 -1
View File
@@ -209,7 +209,7 @@ jobs:
export TEMPLATE=TOKEN_NORMAL
curl -X POST http://0.0.0.0:${FLASK_PORT}/switch \
-H "Content-Type: application/json" \
-d "{\"--model\": \"/MODELDATA/ERNIE-4.5-VL-28B-A3B-Thinking\", \"--reasoning-parser\": \"ernie-45-vl-thinking\", \"--tool-call-parser\": \"ernie-45-vl-thinking\", \"--tensor-parallel-size\": 1, \"--quantization\": \"wint4\", \"--max-model-len\": 131072, \"--max-num-seqs\": 32}"
-d "{\"--model\": \"/MODELDATA/ERNIE-4.5-VL-28B-A3B-Thinking\", \"--reasoning-parser\": \"ernie-45-vl-thinking\", \"--tool-call-parser\": \"ernie-45-vl-thinking\", \"--tensor-parallel-size\": 1, \"--quantization\": \"wint4\", \"--max-model-len\": 131072, \"--max-num-seqs\": 32, \"--no-enable-prefix-caching\": true}"
check_service 90
python -m pytest -sv test_prompt_ids.py || TEST_EXIT_CODE=1