xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 23:15:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Rocm][CI] Fix test_speculator_eagle3 by skipping the CompressedTensorw4a16 Model (#30001)

Browse Source 
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: Alexei-V-Ivanov-AMD <156011006+Alexei-V-Ivanov-AMD@users.noreply.github.com>
This commit is contained in:
Charlie Fu 2025-12-04 01:52:28 -06:00 committed by GitHub
parent fd68e909db
commit 9aa33a74b0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tests/v1/spec_decode/test_speculators_eagle3.py
View File

@ -5,6 +5,7 @@ import torch
from vllm.config import SpeculativeConfig from vllm.config import SpeculativeConfig
from vllm.model_executor.models.interfaces import supports_eagle3 from vllm.model_executor.models.interfaces import supports_eagle3
from vllm.platforms import current_platform
@pytest.mark.parametrize( @pytest.mark.parametrize(
@ -21,6 +22,10 @@ from vllm.model_executor.models.interfaces import supports_eagle3
pytest.param( pytest.param(
"nm-testing/Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16", "nm-testing/Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16",
id="qwen3-eagle3-speculator-w4a16-verifier", id="qwen3-eagle3-speculator-w4a16-verifier",
marks=pytest.mark.skipif(
current_platform.is_rocm(),
reason="The tests are skipped on rocm platform.",
),
), ),
], ],
) )