Initial import: bare-metal stacks, Server UI, GPU fan, tutorials.

Infrastructure configs for GMKtec K11 (Docker, vLLM, LocalAI, ComfyUI,
control-plane, gpu-fan agent, Server UI with CLI/file explorer/GPU fan curve).

Co-authored-by: Cursor <cursoragent@cursor.com>

stacks/localai/profiles/bge-m3-FP16-embedding.yaml.example

@@ -0,0 +1,16 @@
+# BGE-M3 embedding model for LocalAI (llama-cpp backend).
+# Copy to /data/apps/localai/models/bge-m3-FP16.gguf.yaml after gallery import.
+#
+# GGUF: bge-m3-FP16.gguf (~1.1 GB) in same directory as this YAML.
+# API id: bge-m3-FP16.gguf
+# Vector dimensions: 1024
+
+name: bge-m3-FP16.gguf
+backend: llama-cpp
+embeddings: true
+description: BGE-M3 embedding model (1024 dims)
+known_usecases:
+  - embedding
+parameters:
+  model: bge-m3-FP16.gguf
+context_size: 8192

stacks/localai/profiles/bge-reranker-v2-m3-FP16-rerank.yaml.example

@@ -0,0 +1,27 @@
+# BGE-Reranker-v2-m3 for LocalAI (llama-cpp / cuda13-llama-cpp backend).
+# Copy to /data/apps/localai/models/bge-reranker-v2-m3-FP16.gguf.yaml after GGUF download.
+#
+# GGUF: bge-reranker-v2-m3-FP16.gguf (~1.1 GB) in same directory as this YAML.
+# API id: bge-reranker-v2-m3-FP16.gguf
+# Endpoint: POST /v1/rerank
+#
+# Do NOT use backend: rerankers for GGUF — that backend is for HuggingFace transformers.
+# cuda13-llama-cpp is selected automatically on the cuda-13 image when backend: llama-cpp.
+
+name: bge-reranker-v2-m3-FP16.gguf
+backend: llama-cpp
+reranking: true
+embeddings: false
+description: BGE-Reranker-v2-m3 cross-encoder (FP16 GGUF)
+known_usecases:
+  - rerank
+parameters:
+  model: bge-reranker-v2-m3-FP16.gguf
+context_size: 8192
+template:
+  use_tokenizer_template: true
+function:
+  grammar:
+    disable: true
+options:
+  - use_jinja:true

stacks/localai/profiles/gemma-4-12b-q4-kv-q8.yaml.example

@@ -0,0 +1,32 @@
+# Szablon: Gemma 4 12B Q4_0 z kwantyzowanym KV cache (q8_0)
+#
+# Zastosowanie na serwerze:
+#   ./scripts/apply-kv-profile.sh gemma-4-12b-it-qat-q4_0
+# lub skopiuj sekcję parameters do /data/apps/localai/models/<nazwa>.yaml
+#
+# Dokumentacja: coding-agent/KV-CACHE.md
+
+name: gemma-4-12b-it-qat-q4_0
+backend: llama-cpp
+mmproj: llama-cpp/mmproj/gemma-4-12B-it-qat-q4_0-gguf/mmproj-gemma-4-12b-it-qat-q4_0.gguf
+known_usecases:
+  - chat
+options:
+  - use_jinja:true
+parameters:
+  model: llama-cpp/models/gemma-4-12B-it-qat-q4_0-gguf/gemma-4-12b-it-qat-q4_0.gguf
+  cache_type_k: q8_0
+  cache_type_v: q8_0
+  flash_attention: true
+  context_size: 8192
+  temperature: 1
+  top_p: 0.95
+  top_k: 64
+  repeat_penalty: 1
+  min_p: 0
+template:
+  use_tokenizer_template: true
+function:
+  automatic_tool_parsing_fallback: true
+  grammar:
+    disable: true