minor updates to cpu deployment

Signed-off-by: Nir Rozenbaum <[email protected]>

Author: nirrozenbaum

config/manifests/vllm/cpu-deployment.yaml

@@ -26,8 +26,8 @@ spec:
           - "--max-loras"
           - "4"
           - "--lora-modules"
-          - '{"name": "tweet-summary-0", "path": "/adapters/hub/models--ai-blond--Qwen-Qwen2.5-Coder-1.5B-Instruct-lora/snapshots/9cde18d8ed964b0519fb481cca6acd936b2ca811"}'
-          - '{"name": "tweet-summary-1", "path": "/adapters/hub/models--ai-blond--Qwen-Qwen2.5-Coder-1.5B-Instruct-lora/snapshots/9cde18d8ed964b0519fb481cca6acd936b2ca811"}'
+          - '{"name": "tweet-summary-0", "path": "/adapters/ai-blond/Qwen-Qwen2.5-Coder-1.5B-Instruct-lora_0"}'
+          - '{"name": "tweet-summary-1", "path": "/adapters/ai-blond/Qwen-Qwen2.5-Coder-1.5B-Instruct-lora_1"}'
           env:
             - name: PORT
               value: "8000"
@@ -38,6 +38,8 @@ spec:
                   key: token
             - name: VLLM_ALLOW_RUNTIME_LORA_UPDATING
               value: "true"
+            - name: VLLM_CPU_KVCACHE_SPACE
+              value: "4"
           ports:
             - containerPort: 8000
               name: http