Initial SQL-only 1C adapter baseline

core/deploy/docker-gpu/llama-cpp/qwen3-coder-q6.env.example

@@ -0,0 +1,19 @@
+# Qwen3-Coder Q6 GPU llama.cpp settings for docker-gpu.cin.su.
+# This model is too large to keep online together with SDXL/vLLM on a 24 GiB RTX 4090.
+
+LLAMA_CONTAINER_NAME=llm-llama-qwen3-coder-q6-test
+LLAMA_IMAGE=ghcr.io/ggml-org/llama.cpp:server-cuda
+LLAMA_HOST_PORT=8081
+LLAMA_MODEL_PATH=/models/gguf/1c/qwen3-coder-30b-a3b-instruct-q6_k/Qwen3-Coder-30B-A3B-Instruct-Q6_K.gguf
+LLAMA_SERVED_MODEL_NAME=qwen3-coder-1c-q6
+LLAMA_CTX_SIZE=8192
+LLAMA_GPU_LAYERS=auto
+LLAMA_THREADS=12
+LLAMA_PARALLEL=1
+LLAMA_FIT=on
+LLAMA_REASONING=auto
+LLAMA_REASONING_FORMAT=none
+LLAMA_CHAT_TEMPLATE=chatml
+# Optional future LoRA path after converting the trained adapter to GGUF for llama.cpp:
+# LLAMA_LORA_PATH=/models/adapters/1c/qwen3-coder-30b-a3b-1c-lora-v1.gguf
+HOST_MODELS_DIR=Z:/LLM/models