Add tutorial for deploying DeepSeek-R1-Distill-Llama3.1-8B (#305)

Author: javierdlrm

integrations/vllm/deepseek-r1-distill-llama31-8b/deepseek_vllmconfig.yaml

@@ -0,0 +1,5 @@
+dtype: "half"
+max_model_len: 2048
+gpu_memory_utilization: 0.96
+enable_reasoning: true
+reasoning_parser: "deepseek_r1"