Fix Phase 1 server validation defects

2026-07-13 05:30:39 +05:30
1 parent 55a2a41089
commit a2ee7247d5
@@ -32,7 +32,7 @@
    vllm_tensor_parallel: 1
    vllm_gpu_memory_util: "0.85"
    vllm_max_model_len: 4096
-    vllm_quantization: "awq"
+    vllm_quantization: ""          # Phi-3 source model is not AWQ-quantized

    # ── Ollama — lightweight models ───────────────
    ollama_default_model: "phi3:mini"