fix qwen vllm

Galaxy-Ding · May 12, 2024 · b89e711 · b89e711
1 parent 559e0c4
commit b89e711
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/Qwen1.5/07-Qwen1.5-7B-Chat vLLM 推理部署调用.md b/Qwen1.5/07-Qwen1.5-7B-Chat vLLM 推理部署调用.md
@@ -288,8 +288,8 @@ python benchmark_throughput.py \
 	--output-len 128 \
 	--num-prompts 25 \
 	--seed 2024 \
-	--dtype float16
-    --hf_max_batch_size 25
+	--dtype float16 \
+    --hf-max-batch-size 25
 ```
 得到的结果如下所示：
 ```