We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 52ad455 commit 7454665Copy full SHA for 7454665
tests/e2e/vLLM/configs/w4a16_channel_quant_moe.yaml
@@ -1,7 +1,7 @@
1
cadence: "nightly"
2
test_type: "regression"
3
-model: Qwen/Qwen3-Omni-30B-A3B-Instruct
4
-model_class: "Qwen3OmniMoeForConditionalGeneration"
+model: Qwen/Qwen3-VL-30B-A3B-Instruct
+model_class: "Qwen3VLMoeForConditionalGeneration"
5
scheme: W4A16
6
dataset_id: HuggingFaceH4/ultrachat_200k
7
dataset_split: train_sft
0 commit comments