init v0.23.0

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

tests/e2e/nightly/single_node/models/configs/Kimi-K2-Thinking.yaml

@@ -0,0 +1,52 @@
+# ==========================================
+# ACTUAL TEST CASES
+# ==========================================
+
+test_cases:
+  - name: "Kimi-K2-Thinking-TP16-Case"
+    model: "moonshotai/Kimi-K2-Thinking"
+    envs:
+      HCCL_BUFFSIZE: "1024"
+      TASK_QUEUE_ENABLE: "1"
+      OMP_PROC_BIND: "false"
+      HCCL_OP_EXPANSION_MODE: "AIV"
+      PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+      SERVER_PORT: "DEFAULT_PORT"
+    server_cmd:
+      - "--tensor-parallel-size"
+      - "16"
+      - "--port"
+      - "$SERVER_PORT"
+      - "--max-model-len"
+      - "8192"
+      - "--max-num-batched-tokens"
+      - "8192"
+      - "--max-num-seqs"
+      - "12"
+      - "--gpu-memory-utilization"
+      - "0.9"
+      - "--trust-remote-code"
+      - "--enable-expert-parallel"
+      - "--no-enable-prefix-caching"
+    benchmarks:
+      acc:
+        case_type: accuracy
+        dataset_path: vllm-ascend/gsm8k-lite
+        request_conf: vllm_api_general_chat
+        dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
+        max_out_len: 4096
+        batch_size: 32
+        baseline: 95
+        threshold: 10
+      perf:
+        case_type: performance
+        dataset_path: vllm-ascend/GSM8K-in3500-bs400
+        request_conf: vllm_api_stream_chat
+        dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
+        num_prompts: 512
+        max_out_len: 256
+        batch_size: 64
+        trust_remote_code: true
+        request_rate: 11.2
+        baseline: 1
+        threshold: 0.97