init v0.11.0rc0

benchmarks/ops/ben_vocabparallelembedding.py

@@ -112,7 +112,7 @@ def test_get_masked_input_and_mask(
 
     # Define custom function
     def custom_fn():
-        return torch.ops._C.get_masked_input_and_mask(
+        return torch.ops._C_ascend.get_masked_input_and_mask(
             input_tensor,
             test_case["org_start"],
             test_case["org_end"],

benchmarks/scripts/run-performance-benchmarks.sh

@@ -78,7 +78,9 @@ kill_npu_processes() {
   ps -aux
   lsof -t -i:8000 | xargs -r kill -9
   pgrep python3 | xargs -r kill -9
-  
+  # vLLM now names the process with VLLM prefix after https://github.com/vllm-project/vllm/pull/21445
+  pgrep VLLM | xargs -r kill -9
+
   sleep 4
   rm -rf ~/.config/vllm
 

benchmarks/tests/serving-tests.json

@@ -23,7 +23,8 @@
       "hf_split": "train",
       "endpoint": "/v1/chat/completions",
       "dataset_path": "lmarena-ai/vision-arena-bench-v0.1",
-      "num_prompts": 200
+      "num_prompts": 200,
+      "no_stream": ""
     }
   },
   {