Qwen3-30B-A3B-Thinking_offline2

README.md

@@ -211,17 +211,6 @@ Qwen3-30B-A3B-Thinking-2507在DCU(K100_AI)与GPU(A800)离线推理的平均绝
 DCU(K100_AI)与GPU(A800)离线推理Qwen3-30B-A3B-Thinking-2507精度一致，推理框架：vllm
 
 
-
-
-
-
-
-
-
-
-
-
-
 ### vllm在线推理Qwen3-30B-A3B
 ```bash
 ## Qwen3-30B-A3B 至少需要双卡部署

infer/offline/infer_vllm.py

@@ -113,7 +113,7 @@ def main(args: dict):
                     first_10_logprobs_to_save.append(logprob_value)
 
 
-    output_filename = './Qwen3-30B-A3B-Thinking-2507_logprobs_A800_fp16.json'
+    output_filename = './Qwen3-30B-A3B-Thinking-2507_logprobs_K100AI_fp16.json'
     with open(output_filename, 'w') as f:
         json.dump(first_10_logprobs_to_save, f, indent=2)