feat(bench): add speed-bench tool service for drafter benchmarks

Runs llama.cpp's SPEED-Bench client (pinned commit) against
llama-server over the compose network, in the tools profile.

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

docker-compose.yml

@@ -67,6 +67,16 @@ services:
         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/operations.md#speed-bench
+  speed-bench:
+    profiles: ["tools"]
+    build: ./speed-bench
+    entrypoint: ["python", "/app/speed_bench.py", "--url", "http://llama-server:8080"]
+    volumes:
+      - hf-cache:/root/.cache/huggingface
+      - ./bench-results:/results
+    networks: [ai-stack]
+
   # see docs/architecture.md#omniroute; runtime config lives in its dashboard, see docs/gateway.md
   omniroute:
     image: diegosouzapw/omniroute:latest
@@ -127,3 +137,4 @@ volumes:
   models:
   omniroute-data:
   qdrant-data:
+  hf-cache: