fix server config

Author: tastelikefeet

cookbook/client/tinker/megatron/server_config.yaml

@@ -63,6 +63,7 @@ applications:
           target_ongoing_requests: 16
         ray_actor_options:
           num_cpus: 0.1
+          num_gpus: 1
 
   # 3. Sampler Service - Runs inference / sampling using vLLM engine
   #    Used for generating text from the model (e.g., evaluating LoRA results).