biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build] Replaced some models on tests for smaller ones (#9570)

Browse Source 
Signed-off-by: Wallas Santos <wallashss@ibm.com>
This commit is contained in:
Wallas Henrique
2024-10-22 01:52:14 -03:00
committed by GitHub
parent 74692421f7
commit c0292211ce
8 changed files with 15 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/basic_correctness/test_basic_correctness.py
View File

@@ -19,7 +19,7 @@ from ..utils import multi_gpu_test
MODELS = [
"facebook/opt-125m",
"meta-llama/Llama-2-7b-hf",
"meta-llama/Llama-3.2-1B",
]
TARGET_TEST_SUITE = os.environ.get("TARGET_TEST_SUITE", "L4")

2
tests/basic_correctness/test_chunked_prefill.py
View File

@@ -16,7 +16,7 @@ from ..utils import multi_gpu_test
MODELS = [
"facebook/opt-125m",
"meta-llama/Llama-2-7b-hf",
"meta-llama/Llama-3.2-1B",
]

4
tests/basic_correctness/test_cpu_offload.py
View File

@@ -2,5 +2,5 @@ from ..utils import compare_two_settings
def test_cpu_offload():
compare_two_settings("meta-llama/Llama-2-7b-hf", [],
["--cpu-offload-gb", "4"])
compare_two_settings("meta-llama/Llama-3.2-1B", [],
["--cpu-offload-gb", "1"])