feat(llm): switch to DFlash2 speculative decoding, drop qwen-classifier

Replace MTP with draft-dflash and a separate DFlash2 drafter GGUF.
Remove the qwen-classifier backend to free VRAM (GPU was at 100%).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

docker-compose.yml

@@ -28,8 +28,9 @@ services:
       --cache-type-k q8_0
       --cache-type-v q8_0
       --cache-reuse 256
-      --spec-type draft-mtp 
-      --spec-draft-n-max 2
+      --spec-type draft-dflash
+      -md /models/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q4_K_M.gguf}
+      --spec-draft-n-max ${LLAMA_SPEC_N_MAX:-7}
       --jinja
     # see docs/architecture.md#llama-server (flags), docs/network-access.md#backends (no host port)
     expose:
@@ -37,43 +38,6 @@ services:
     restart: unless-stopped
     networks: [ai-stack]
 
-  # see docs/architecture.md#qwen-classifier
-  qwen-classifier:
-    image: ghcr.io/ggml-org/llama.cpp:server-rocm
-    container_name: qwen-classifier
-    devices:
-      - /dev/kfd
-      - /dev/dri
-    group_add:
-      - "${HOST_VIDEO_GID:?run scripts/update.sh first to resolve this}"
-      - "${HOST_RENDER_GID:?run scripts/update.sh first to resolve this}"
-    security_opt:
-      - seccomp=unconfined
-    ipc: host
-    # see docs/architecture.md#gpu-access
-    environment:
-      - GPU_MAX_HW_QUEUES=1
-    volumes:
-      - models:/models
-    command: >
-      -m /models/${LLAMA_CLASSIFIER_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf}
-      --host 0.0.0.0
-      --port 8080
-      --n-gpu-layers 28
-      --ctx-size 50000
-      --parallel 1
-      --batch-size 512
-      --ubatch-size 128
-      --flash-attn on
-      --reasoning off
-      --cache-type-k q4_0
-      --cache-type-v q4_0
-      --jinja
-    expose:
-      - "8080"
-    restart: unless-stopped
-    networks: [ai-stack]
-
   # see docs/operations.md#model-downloads (also covers downloader-classifier)
   downloader:
     image: curlimages/curl:latest
@@ -89,7 +53,7 @@ services:
         curl -L --fail --create-dirs -o /models/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
         https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
 
-  downloader-classifier:
+  downloader-draft:
     image: curlimages/curl:latest
     profiles: ["tools"]
     user: root
@@ -98,10 +62,10 @@ services:
     entrypoint: ["sh", "-c"]
     command:
       - >
-        test -f /models/${LLAMA_CLASSIFIER_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf} &&
+        test -f /models/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q4_K_M.gguf} &&
         echo "already downloaded, skipping" ||
-        curl -L --fail --create-dirs -o /models/${LLAMA_CLASSIFIER_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf}
-        https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF/resolve/main/${LLAMA_CLASSIFIER_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf}
+        curl -L --fail --create-dirs -o /models/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q4_K_M.gguf}
+        https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/main/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q4_K_M.gguf}
 
   # see docs/architecture.md#omniroute; runtime config lives in its dashboard, see docs/gateway.md
   omniroute: