+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: ds-inference-params
+data:
+  inference_config.yaml: |
+    vllm:
+      cpu-offload-gb: 0
+      gpu-memory-utilization: 0.95
+      swap-space: 4
+      max-model-len: 131072
+      tensor-parallel-size: 2
+      max-seq-len-to-capture: 8192
+      num-scheduler-steps: 1
+      enable-chunked-prefill: true
+      # see https://docs.vllm.ai/en/latest/serving/engine_args.html for more options.
 ---
 apiVersion: kaito.sh/v1beta1
 kind: Workspace
 metadata:
   name: workspace-deepseek-r1-distill-qwen-14b
 resource:
   instanceType: "Standard_NC24ads_A100_v4"
   labelSelector:
     matchLabels:
       apps: deepseek-r1-distill-qwen-14b
 inference:
   preset:
     name: "deepseek-r1-distill-qwen-14b"
   config: "ds-inference-params"