upload whl

README.md

@@ -49,7 +49,7 @@ docker load -i pytorch2.9.1-ubuntu22.04-dtk26.04-0130-py3.10-20260204.tar.gz
 - 挂载地址`-v` 根据实际模型情况修改
 ```bash
 docker run -it \
-    --shm-size 60g \
+    --shm-size 200g \
     --network=host \
     --name qwen3.5 \
     --privileged \
@@ -110,9 +110,6 @@ export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
 export VLLM_SPEC_DECODE_EAGER=1
 export VLLM_MLA_DISABLE=0
 export VLLM_USE_FLASH_MLA=1
-
-# K100_AI集群建议额外设置的环境变量：
-export VLLM_ENFORCE_EAGER_BS_THRESHOLD=44
 export VLLM_RPC_TIMEOUT=1800000
 
 # 海光CPU绑定核

model.properties

@@ -11,4 +11,4 @@ appCategory=对话问答
 # 框架类型
 frameType=vllm
 # 加速卡类型
-accelerateType=K100AI,BW1000
\ No newline at end of file
+accelerateType=BW1000
\ No newline at end of file