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

[CI][XPU] ep+prefix cache+chunk prefill (#5489)

Browse Source
This commit is contained in:
zccjjj
2025-12-10 19:39:49 +08:00
committed by GitHub
parent a2ab1f4462
commit 03819f30c3
3 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/xpu_ci/test_ep4tp1_online.py
View File

@@ -63,6 +63,7 @@ def test_ep4tp1_online(xpu_env):
"--tensor-parallel-size",
"1",
"--enable-expert-parallel",
"--enable-prefix-caching",
"--data-parallel-size",
"4",
"--max-model-len",

1
tests/xpu_ci/test_ep4tp4_all2all.py
View File

@@ -65,6 +65,7 @@ def test_ep4tp4_all2all(xpu_env):
"--tensor-parallel-size",
"4",
"--enable-expert-parallel",
"--enable-prefix-caching",
"--data-parallel-size",
"1",
"--max-model-len",

1
tests/xpu_ci/test_ep4tp4_online.py
View File

@@ -64,6 +64,7 @@ def test_ep4tp4_online(xpu_env):
"--tensor-parallel-size",
"4",
"--enable-expert-parallel",
"--enable-prefix-caching",
"--data-parallel-size",
"1",
"--max-model-len",