fix vllm error

2026-05-06 01:31:45 +00:00 · 2026-05-06 01:31:45 +00:00 · 2200006c41
commit 2200006c41
parent 5247e6caee
2 changed files with 2 additions and 2 deletions
--- a/apps/base/customer1/hermes-agent/rays-deployment.yaml
+++ b/apps/base/customer1/hermes-agent/rays-deployment.yaml
@ -42,7 +42,7 @@ spec:
                key: XAI_API_KEY 
                
          - name: TELEGRAM_ALLOWED_USERS
-            value: ""        
+            value: "7105451284"        

          # === Local vLLM (OpenAI-compatible) ===
          - name: OPENAI_BASE_URL
--- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml
+++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml
@ -40,7 +40,7 @@ spec:
            - --gpu-memory-utilization=0.98
            - --max-model-len=131072
            - --enable-auto-tool-choice 
-            - --kv-cache=dtype=fp8 
+            - --kv-cache-dtype=fp8 
            - --max-num-batched-tokens=32768
            - --max-num-seqs=16 
            - --trust-remote-code