A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[CI Bugfix] Fix wNa16 kernel not found for test_shared_storage_connector_hashes (#22163)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Tyler Michael Smith committed
Aug 4, 2025 at 01:19 UTC
8ecb3e9e9336ce47e47b61417e24161b38079e93
1 file changed
+1
-1
tests/v1/kv_connector/unit/test_shared_storage_connector.py
+1
-1
@@ -10,7 +10,7 @@ from vllm.assets.image import ImageAsset
10
from vllm.config import KVTransferConfig
11
from vllm.multimodal.utils import encode_image_base64
12
13
-MODEL_NAME = "RedHatAI/Qwen2.5-VL-3B-Instruct-quantized.w4a16"
13
+MODEL_NAME = "RedHatAI/Qwen2.5-VL-3B-Instruct-quantized.w8a8"
14
15
SAMPLING_PARAMS = SamplingParams(temperature=0.0, top_k=1, max_tokens=128)
16