Initial SQL-only 1C adapter baseline

core/deploy/docker-gpu/llama-cpp/.env.example

@@ -0,0 +1,17 @@
+# Copy to .env on the deployment host and adjust values there.
+# Do not commit real tokens, private paths, or credentials.
+
+LLAMA_CONTAINER_NAME=llm-llama-devstral-1c
+LLAMA_IMAGE=ghcr.io/ggml-org/llama.cpp:server-cuda
+LLAMA_HOST_PORT=8080
+LLAMA_MODEL_PATH=/models/gguf/1c/devstral-small-2-24b-instruct-2512-q4_k_m/mistralai_Devstral-Small-2-24B-Instruct-2512-Q4_K_M.gguf
+LLAMA_SERVED_MODEL_NAME=devstral-1c-q4
+LLAMA_CTX_SIZE=32768
+LLAMA_GPU_LAYERS=999
+LLAMA_THREADS=8
+LLAMA_PARALLEL=1
+LLAMA_FIT=off
+LLAMA_REASONING=off
+LLAMA_REASONING_FORMAT=none
+LLAMA_CHAT_TEMPLATE=mistral-v7-tekken
+HOST_MODELS_DIR=/models