Update README.md

README.md

@@ -37,16 +37,16 @@ For reference, the Dense model can be used after compression with FP8 Dynamic.
 export NCCL_P2P_DISABLE=1
 ```
 
-In GPU 2 units, 
+In GPU 2 units, with KV Cache 90%, Max token 32768
 
 ```
 vllm serve BCCard/kanana-1.5-8b-instruct-2505-FP8-Dynamic \
   --tensor-parallel-size 2 \
   --gpu-memory-utilization 0.9  \
-  --max-model-len 8192 \  
-  --enforce-eager \  
+  --max-model-len 32768 \
+  --enforce-eager \
   --api-key bccard \
-  --served-model-name kanana-1.5-8b-instruct
+  --served-model-name kanana-1.5-8b-instruct 
 ```
 
 ## 3. Quantization Code Walk‑Through (Shared Knowledges)