init v0.11.0rc0

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

@@ -1,12 +1,16 @@
 model_name: "deepseek-ai/DeepSeek-V2-Lite"
+runner: "linux-aarch64-a2-2"
+hardware: "Atlas A2 Series"
 tasks:
 - name: "gsm8k"
   metrics:
   - name: "exact_match,strict-match"
-    value: 0.375
+    value: 0.385
   - name: "exact_match,flexible-extract"
-    value: 0.375
+    value: 0.385
 tensor_parallel_size: 2
+batch_size: 32
+gpu_memory_utilization: 0.7
 apply_chat_template: False
 fewshot_as_multiturn: False
 trust_remote_code: True

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

@@ -1,4 +1,6 @@
 model_name: "Qwen/Qwen2.5-VL-7B-Instruct"
+runner: "linux-aarch64-a2-1"
+hardware: "Atlas A2 Series"
 model: "vllm-vlm"
 tasks:
 - name: "mmmu_val"

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

@@ -1,4 +1,6 @@
 model_name: "Qwen/Qwen3-30B-A3B"
+runner: "linux-aarch64-a2-2"
+hardware: "Atlas A2 Series"
 tasks:
 - name: "gsm8k"
   metrics:

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

@@ -1,4 +1,6 @@
 model_name: "Qwen/Qwen3-8B-Base"
+runner: "linux-aarch64-a2-1"
+hardware: "Atlas A2 Series"
 tasks:
 - name: "gsm8k"
   metrics:

tests/e2e/models/configs/accuracy.txt

@@ -1,3 +1,4 @@
+DeepSeek-V2-Lite.yaml
 Qwen3-8B-Base.yaml
 Qwen2.5-VL-7B-Instruct.yaml
 Qwen3-30B-A3B.yaml