init v0.23.0

Signed-off-by: Sun Ruoxi <sunruoxi@4paradigm.com>

tests/e2e/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml

@@ -0,0 +1,23 @@
+model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct"
+model_type: "vllm"
+hardware: "Atlas A2 Series"
+
+serve:
+  tensor_parallel_size: 4
+  dtype: auto
+  max_model_len: 4096
+  gpu_memory_utilization: 0.7
+  trust_remote_code: false
+  enable_expert_parallel: true
+  enforce_eager: true
+
+tasks:
+- name: "ceval-valid_accountant"
+  metrics:
+  - name: "acc,none"
+    value: 0.98
+
+num_fewshot: 5
+apply_chat_template: true
+fewshot_as_multiturn: true
+batch_size: 1