Add max_tokens cap on gpt oss 20b

Author: nwthomas

helm/vllm/values.yaml

@@ -16,7 +16,7 @@ vllm:
     - /bin/sh
     - -c
   args:
-    - "vllm serve openai/gpt-oss-20b --trust-remote-code --enable-chunked-prefill --enable-auto-tool-choice --tool-call-parser openai --reasoning-parser openai_gptoss"
+    - "vllm serve openai/gpt-oss-20b --trust-remote-code --enable-chunked-prefill --enable-auto-tool-choice --tool-call-parser openai --reasoning-parser openai_gptoss --max_tokens 10000"
   gpu:
     enabled: true
     type: "nvidia"