feat: route qwen2.5:3b-instruct to CPU service #20
+1
-1
@@ -36,7 +36,7 @@ data:
|
||||
path: "/v1/chat/completions"
|
||||
|
||||
- name: "qwen2.5:3b-instruct"
|
||||
address: "ornith-predictor.llm-serving:80"
|
||||
address: "qwen-cpu.llm-serving:80"
|
||||
path: "/v1/chat/completions"
|
||||
|
||||
- name: "nomic-ai/nomic-embed-text-v2-moe"
|
||||
|
||||
@@ -25,7 +25,7 @@ stringData:
|
||||
address: "ornith-predictor.llm-serving:80"
|
||||
path: "/v1/chat/completions"
|
||||
- name: "qwen2.5:3b-instruct"
|
||||
address: "ornith-predictor.llm-serving:80"
|
||||
address: "qwen-cpu.llm-serving:80"
|
||||
path: "/v1/chat/completions"
|
||||
- name: "nomic-ai/nomic-embed-text-v2-moe"
|
||||
address: "embeddings-predictor.llm-serving:80"
|
||||
|
||||
Reference in New Issue
Block a user