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>
2026-07-05 12:02:04 +00:00
commit 359afb3a59
153 changed files with 18169 additions and 0 deletions
@@ -0,0 +1,63 @@
+#!/usr/bin/env bash
+# Shared helpers for models.catalog.yaml (simple parser, no PyYAML required).
+
+CATALOG_FILE="${CATALOG_FILE:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/models.catalog.yaml}"
+
+catalog_list_ids() {
+  grep '^  - id:' "${CATALOG_FILE}" | awk '{print $3}'
+}
+
+catalog_get_field() {
+  local model_id="$1"
+  local field="$2"
+  awk -v id="${model_id}" -v key="${field}:" '
+    $0 ~ "^  - id: " id "$" { found=1; next }
+    found && $0 ~ "^  - id:" { exit }
+    found && index($0, key) == 5 { sub(/^    [^:]+: /, ""); print; exit }
+  ' "${CATALOG_FILE}"
+}
+
+catalog_ensure_dirs() {
+  local data_root="${1:-/data}"
+  mkdir -p \
+    "${data_root}/apps/vllm/huggingface" \
+    "${data_root}/apps/gguf/qwen3.6-27b" \
+    "${data_root}/apps/gguf/gemma-4-12b"
+}
+
+catalog_model_downloaded() {
+  local model_id="$1"
+  local runtime
+  runtime="$(catalog_get_field "${model_id}" runtime)"
+
+  case "${runtime}" in
+    vllm)
+      local hf_model
+      hf_model="$(catalog_get_field "${model_id}" hf_model)"
+      local cache="${DATA_ROOT:-/data}/apps/vllm/huggingface"
+      # Heuristic: HF hub cache contains repo name
+      local repo_path
+      repo_path=$(echo "${hf_model}" | tr '/' '--')
+      if find "${cache}/hub" -maxdepth 3 -type d -name "models--${repo_path}" 2>/dev/null | grep -q .; then
+        return 0
+      fi
+      return 1
+      ;;
+    llamacpp)
+      local local_path local_dir gguf_file
+      local_path="$(catalog_get_field "${model_id}" local_path)"
+      local_dir="$(catalog_get_field "${model_id}" local_dir)"
+      gguf_file="$(catalog_get_field "${model_id}" gguf_file)"
+      if [[ -n "${local_path}" && -f "${local_path}" ]]; then
+        return 0
+      fi
+      if [[ -n "${local_dir}" && -n "${gguf_file}" && -f "${local_dir}/${gguf_file}" ]]; then
+        return 0
+      fi
+      return 1
+      ;;
+    *)
+      return 1
+      ;;
+  esac
+}
@@ -0,0 +1,114 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+STACK_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
+
+# shellcheck disable=SC1091
+source "${SCRIPT_DIR}/catalog-lib.sh"
+
+cd "${STACK_DIR}"
+
+if [[ $# -lt 1 ]]; then
+  echo "Usage: $0 <catalog-model-id>"
+  echo ""
+  echo "Available models:"
+  catalog_list_ids | sed 's/^/  /'
+  exit 1
+fi
+
+MODEL_ID="$1"
+
+if ! catalog_list_ids | grep -qx "${MODEL_ID}"; then
+  echo "ERROR: Unknown model id: ${MODEL_ID}"
+  echo "Run: ./scripts/list-models.sh"
+  exit 1
+fi
+
+if [[ -f .env ]]; then
+  set -a
+  # shellcheck disable=SC1091
+  source .env
+  set +a
+fi
+
+DATA_ROOT="${DATA_ROOT:-/data}"
+catalog_ensure_dirs "${DATA_ROOT}"
+
+RUNTIME="$(catalog_get_field "${MODEL_ID}" runtime)"
+NAME="$(catalog_get_field "${MODEL_ID}" name)"
+
+echo "=== Download: ${NAME} (${MODEL_ID}) ==="
+echo "Runtime: ${RUNTIME}"
+echo ""
+
+case "${RUNTIME}" in
+  vllm)
+    HF_MODEL="$(catalog_get_field "${MODEL_ID}" hf_model)"
+    echo "Target: Hugging Face cache at ${DATA_ROOT}/apps/vllm/huggingface"
+    echo "Model:  ${HF_MODEL}"
+    echo ""
+
+    HF_ENV=()
+    if [[ -n "${HF_TOKEN:-}" ]]; then
+      HF_ENV=(-e "HF_TOKEN=${HF_TOKEN}")
+    fi
+
+    docker run --rm \
+      "${HF_ENV[@]}" \
+      -v "${DATA_ROOT}/apps/vllm/huggingface:/root/.cache/huggingface" \
+      ghcr.io/huggingface/huggingface-cli:latest \
+      download "${HF_MODEL}"
+  ;;
+  llamacpp)
+    DOWNLOAD_URL="$(catalog_get_field "${MODEL_ID}" download_url)"
+    LOCAL_PATH="$(catalog_get_field "${MODEL_ID}" local_path)"
+    LOCAL_DIR="$(catalog_get_field "${MODEL_ID}" local_dir)"
+    GGUF_FILE="$(catalog_get_field "${MODEL_ID}" gguf_file)"
+    MMPROJ_URL="$(catalog_get_field "${MODEL_ID}" mmproj_url)"
+    MMPROJ_FILE="$(catalog_get_field "${MODEL_ID}" mmproj_file)"
+
+    if [[ -n "${LOCAL_PATH}" ]]; then
+      DEST="${LOCAL_PATH}"
+      mkdir -p "$(dirname "${DEST}")"
+      if [[ -f "${DEST}" ]]; then
+        echo "Already exists: ${DEST}"
+      else
+        echo "Downloading ${DEST} ..."
+        wget -c -O "${DEST}" "${DOWNLOAD_URL}"
+      fi
+    elif [[ -n "${LOCAL_DIR}" && -n "${GGUF_FILE}" ]]; then
+      mkdir -p "${LOCAL_DIR}"
+      DEST="${LOCAL_DIR}/${GGUF_FILE}"
+      if [[ -f "${DEST}" ]]; then
+        echo "Already exists: ${DEST}"
+      else
+        echo "Downloading ${DEST} ..."
+        wget -c -O "${DEST}" "${DOWNLOAD_URL}"
+      fi
+      if [[ -n "${MMPROJ_URL}" && -n "${MMPROJ_FILE}" ]]; then
+        MMPROJ_DEST="${LOCAL_DIR}/${MMPROJ_FILE}"
+        if [[ -f "${MMPROJ_DEST}" ]]; then
+          echo "Already exists: ${MMPROJ_DEST}"
+        else
+          echo "Downloading ${MMPROJ_DEST} ..."
+          wget -c -O "${MMPROJ_DEST}" "${MMPROJ_URL}"
+        fi
+      fi
+    else
+      echo "ERROR: Catalog entry missing local_path or local_dir/gguf_file"
+      exit 1
+    fi
+
+    echo ""
+    echo "GGUF saved for future llama.cpp stack (stacks/llamacpp/README.md)."
+    echo "Standard vLLM cannot load .gguf files."
+  ;;
+  *)
+    echo "ERROR: Unknown runtime: ${RUNTIME}"
+    exit 1
+    ;;
+esac
+
+echo ""
+echo "Done."
@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+STACK_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
+
+# shellcheck disable=SC1091
+source "${SCRIPT_DIR}/catalog-lib.sh"
+
+cd "${STACK_DIR}"
+
+if [[ -f .env ]]; then
+  set -a
+  # shellcheck disable=SC1091
+  source .env
+  set +a
+fi
+
+DATA_ROOT="${DATA_ROOT:-/data}"
+catalog_ensure_dirs "${DATA_ROOT}"
+
+echo "=== Model catalog ==="
+echo "Catalog: ${CATALOG_FILE}"
+echo "Data:    ${DATA_ROOT}"
+echo ""
+
+printf "%-24s %-10s %-8s %s\n" "ID" "RUNTIME" "ON DISK" "NAME"
+printf "%-24s %-10s %-8s %s\n" "----" "-------" "-------" "----"
+
+while IFS= read -r model_id; do
+  name="$(catalog_get_field "${model_id}" name)"
+  runtime="$(catalog_get_field "${model_id}" runtime)"
+  if catalog_model_downloaded "${model_id}"; then
+    on_disk="yes"
+  else
+    on_disk="no"
+  fi
+  printf "%-24s %-10s %-8s %s\n" "${model_id}" "${runtime}" "${on_disk}" "${name}"
+done < <(catalog_list_ids)
+
+echo ""
+echo "Download on demand:  ./scripts/download-model.sh <id>"
+echo "Switch vLLM profile: ./scripts/switch-model.sh <profile-name>"
+echo ""
+echo "Profiles in profiles/:"
+ls -1 "${STACK_DIR}/profiles/"*.env 2>/dev/null | xargs -n1 basename | sed 's/^/  /' || true
@@ -0,0 +1,88 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+STACK_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
+
+# shellcheck disable=SC1091
+source "${SCRIPT_DIR}/catalog-lib.sh"
+
+cd "${STACK_DIR}"
+
+PROFILE_ARG="${1:-}"
+
+if [[ -n "${PROFILE_ARG}" ]]; then
+  PROFILE_FILE="${STACK_DIR}/profiles/${PROFILE_ARG}.env"
+  if [[ ! -f "${PROFILE_FILE}" ]]; then
+    echo "ERROR: Profile not found: ${PROFILE_ARG}"
+    echo "       Available:"
+    ls -1 "${STACK_DIR}/profiles/"*.env 2>/dev/null | xargs -n1 basename | sed 's/\.env$//' | sed 's/^/         /'
+    exit 1
+  fi
+  cp "${PROFILE_FILE}" .env
+  echo "Applied profile: ${PROFILE_ARG}"
+fi
+
+if [[ ! -f .env ]]; then
+  echo "ERROR: .env not found. Run: cp .env.example .env"
+  echo "       Or use a profile: ./scripts/start.sh qwen3.6-27b-awq-128k"
+  exit 1
+fi
+
+set -a
+# shellcheck disable=SC1091
+source .env
+set +a
+
+DATA_ROOT="${DATA_ROOT:-/data}"
+
+if [[ -z "${VLLM_MODEL:-}" ]]; then
+  echo "ERROR: VLLM_MODEL is empty in .env"
+  echo "       Set a model, use a profile, or run:"
+  echo "       ./scripts/download-model.sh qwen3.6-27b-awq-vllm"
+  echo "       ./scripts/switch-model.sh qwen3.6-27b-awq-128k"
+  exit 1
+fi
+
+if [[ "${VLLM_MODEL}" == *".gguf"* ]]; then
+  echo "ERROR: VLLM_MODEL points to a .gguf file — standard vLLM cannot load GGUF."
+  echo "       GGUF models are in models.catalog.yaml for future llama.cpp (stacks/llamacpp/)."
+  echo "       For vLLM use AWQ from Hugging Face, e.g.:"
+  echo "       ./scripts/download-model.sh qwen3.6-27b-awq-vllm"
+  echo "       ./scripts/switch-model.sh qwen3.6-27b-awq-128k"
+  exit 1
+fi
+
+if ! mountpoint -q "${DATA_ROOT}" 2>/dev/null; then
+  echo "ERROR: ${DATA_ROOT} is not mounted"
+  echo "       Complete disk setup (tutorial 04 part A) first"
+  exit 1
+fi
+
+catalog_ensure_dirs "${DATA_ROOT}"
+
+if ! docker info &>/dev/null; then
+  echo "ERROR: Docker is not running"
+  exit 1
+fi
+
+chmod +x "${SCRIPT_DIR}/vllm-entrypoint.sh" 2>/dev/null || true
+
+echo "=== vLLM stack ==="
+echo "Model:       ${VLLM_MODEL}"
+echo "Served as:   ${SERVED_MODEL_NAME:-qwen3.6-27b}"
+echo "Context:     ${MAX_MODEL_LEN:-131072} tokens"
+echo "KV cache:    ${KV_CACHE_DTYPE:-fp8}"
+echo "Quantize:    ${QUANTIZATION:-(none)}"
+echo "Data root:   ${DATA_ROOT}"
+echo ""
+
+docker compose --profile vllm pull
+docker compose --profile vllm up -d
+
+echo ""
+echo "Started. Follow logs:"
+echo "  docker compose --profile vllm logs -f vllm"
+echo ""
+echo "Test when ready:"
+echo "  curl -s http://localhost:${VLLM_PORT:-8000}/v1/models | jq ."
@@ -0,0 +1,73 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+STACK_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
+
+# shellcheck disable=SC1091
+source "${SCRIPT_DIR}/catalog-lib.sh"
+
+cd "${STACK_DIR}"
+
+PROFILE="${1:-}"
+
+if [[ -z "${PROFILE}" ]]; then
+  echo "Usage: $0 <profile-name>"
+  echo ""
+  echo "Profiles:"
+  ls -1 "${STACK_DIR}/profiles/"*.env 2>/dev/null | xargs -n1 basename | sed 's/\.env$//' | sed 's/^/  /'
+  exit 1
+fi
+
+PROFILE_FILE="${STACK_DIR}/profiles/${PROFILE}.env"
+if [[ ! -f "${PROFILE_FILE}" ]]; then
+  echo "ERROR: Profile not found: ${PROFILE_FILE}"
+  echo ""
+  echo "Available profiles:"
+  ls -1 "${STACK_DIR}/profiles/"*.env 2>/dev/null | xargs -n1 basename | sed 's/\.env$//' | sed 's/^/  /'
+  exit 1
+fi
+
+if [[ -f .env ]]; then
+  set -a
+  # shellcheck disable=SC1091
+  source .env
+  set +a
+fi
+
+DATA_ROOT="${DATA_ROOT:-/data}"
+catalog_ensure_dirs "${DATA_ROOT}"
+
+echo "=== Switch vLLM profile: ${PROFILE} ==="
+cp "${PROFILE_FILE}" .env
+
+set -a
+# shellcheck disable=SC1091
+source .env
+set +a
+
+if [[ "${VLLM_MODEL:-}" == *".gguf"* ]]; then
+  echo "ERROR: VLLM_MODEL points to a .gguf file — vLLM does not support GGUF."
+  echo "       Use stacks/llamacpp (future) or an AWQ Hugging Face model."
+  echo "       See: ./scripts/list-models.sh"
+  exit 1
+fi
+
+if [[ -z "${VLLM_MODEL:-}" ]]; then
+  echo "ERROR: Profile has empty VLLM_MODEL"
+  exit 1
+fi
+
+echo "Model:     ${VLLM_MODEL}"
+echo "Served as: ${SERVED_MODEL_NAME:-qwen3.6-27b}"
+echo "Context:   ${MAX_MODEL_LEN:-131072}"
+echo ""
+
+if docker compose --profile vllm ps -q vllm 2>/dev/null | grep -q .; then
+  echo "Restarting vLLM container ..."
+  docker compose --profile vllm down
+  "${SCRIPT_DIR}/start.sh"
+else
+  echo "vLLM not running. Start with:"
+  echo "  ./scripts/start.sh"
+fi
@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ARGS=(
+  --model "${VLLM_MODEL}"
+  --served-model-name "${SERVED_MODEL_NAME:-qwen3.6-27b}"
+  --host 0.0.0.0
+  --port 8000
+  --max-model-len "${MAX_MODEL_LEN:-131072}"
+  --max-num-seqs "${MAX_NUM_SEQS:-1}"
+  --gpu-memory-utilization "${GPU_MEMORY_UTILIZATION:-0.95}"
+  --kv-cache-dtype "${KV_CACHE_DTYPE:-fp8}"
+  --trust-remote-code
+)
+
+if [[ -n "${QUANTIZATION:-}" ]]; then
+  ARGS+=(--quantization "${QUANTIZATION}")
+fi
+
+if [[ -n "${VLLM_EXTRA_ARGS:-}" ]]; then
+  # shellcheck disable=SC2206
+  EXTRA=( ${VLLM_EXTRA_ARGS} )
+  ARGS+=("${EXTRA[@]}")
+fi
+
+exec vllm serve "${ARGS[@]}"