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

3
tests/compile/test_basic_correctness.py
View File

@@ -13,8 +13,7 @@ from ..utils import compare_all_settings
@pytest.mark.parametrize(
"model, model_args, pp_size, tp_size, attn_backend, method, fullgraph",
[
("meta-llama/Meta-Llama-3-8B", [], 2, 2, "FLASH_ATTN", "generate",
True),
("meta-llama/Llama-3.2-1B", [], 2, 2, "FLASH_ATTN", "generate", True),
("nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token-2048-Samples",
["--quantization", "compressed-tensors"
], 1, 1, "FLASH_ATTN", "generate", True),