v0.10.1rc1

tests/e2e/models/configs/DeepSeek-V2-Lite.yaml

@@ -0,0 +1,13 @@
+model_name: "deepseek-ai/DeepSeek-V2-Lite"
+tasks:
+- name: "gsm8k"
+  metrics:
+  - name: "exact_match,strict-match"
+    value: 0.375
+  - name: "exact_match,flexible-extract"
+    value: 0.375
+tensor_parallel_size: 2
+apply_chat_template: False
+fewshot_as_multiturn: False
+trust_remote_code: True
+enforce_eager: True

tests/e2e/models/configs/Qwen2.5-VL-7B-Instruct.yaml

@@ -0,0 +1,8 @@
+model_name: "Qwen/Qwen2.5-VL-7B-Instruct"
+model: "vllm-vlm"
+tasks:
+- name: "mmmu_val"
+  metrics:
+  - name: "acc,none"
+    value: 0.51
+max_model_len: 8192

tests/e2e/models/configs/Qwen3-30B-A3B.yaml

@@ -0,0 +1,18 @@
+model_name: "Qwen/Qwen3-30B-A3B"
+tasks:
+- name: "gsm8k"
+  metrics:
+  - name: "exact_match,strict-match"
+    value: 0.89
+  - name: "exact_match,flexible-extract"
+    value: 0.85
+- name: "ceval-valid"
+  metrics:
+  - name: "acc,none"
+    value: 0.84
+num_fewshot: 5
+gpu_memory_utilization: 0.6
+enable_expert_parallel: True
+tensor_parallel_size: 2
+apply_chat_template: False
+fewshot_as_multiturn: False

tests/e2e/models/configs/Qwen3-8B-Base.yaml

@@ -0,0 +1,13 @@
+model_name: "Qwen/Qwen3-8B-Base"
+tasks:
+- name: "gsm8k"
+  metrics:
+  - name: "exact_match,strict-match"
+    value: 0.82
+  - name: "exact_match,flexible-extract"
+    value: 0.83
+- name: "ceval-valid"
+  metrics:
+  - name: "acc,none"
+    value: 0.82
+num_fewshot: 5

tests/e2e/models/configs/accuracy.txt

@@ -0,0 +1,3 @@
+Qwen3-8B-Base.yaml
+Qwen2.5-VL-7B-Instruct.yaml
+Qwen3-30B-A3B.yaml