diff --git a/stacks/fish-s2/compose.yaml b/stacks/fish-s2/compose.yaml
index 8543500..9282674 100644
--- a/stacks/fish-s2/compose.yaml
+++ b/stacks/fish-s2/compose.yaml
@@ -80,6 +80,11 @@ services:
       - ${FISH_S2_REFERENCE_DIR}:/app/references
       # Persistent HF cache so model re-pull only happens on first deploy.
       - ${FISH_S2_CACHE_DIR}:/app/hf_cache
+    # Pass --half to start_server.sh → enables fp16 inference on the
+    # LLM half. Speeds up the autoregressive loop (the dominant cost
+    # in TTFB). Also enables the streaming path's faster total time.
+    # build_compile_args() echoes unknown args back to the exec line.
+    command: ["--half"]
     healthcheck:
       # Fish ships /v1/health on the API server. python urllib instead
       # of curl because the upstream image is python-based and may not
diff --git a/stacks/voxtral/compose.yaml b/stacks/voxtral/compose.yaml
index 2c089df..6964df2 100644
--- a/stacks/voxtral/compose.yaml
+++ b/stacks/voxtral/compose.yaml
@@ -37,6 +37,12 @@ services:
     volumes:
       - ${VOXTRAL_CACHE_DIR}:/root/.cache/huggingface
       - ${VOXTRAL_VOICES_DIR}:/voices:ro
+      # Patched stage config — bundled YAML hardcodes
+      # gpu_memory_utilization: 0.8 on the language_model stage which
+      # OOMs anywhere we have other models resident on the same GPU.
+      # Mount our own copy at a custom path; the --stage-configs-path
+      # flag below points at it.
+      - /opt/docker/conf/voxtral/voxtral_tts.yaml:/etc/voxtral/voxtral_tts.yaml:ro
     # vllm/vllm-omni image has no default ENTRYPOINT or CMD — the
     # container init expected --model=... as argv[0]. Set entrypoint
     # to `vllm serve` (the standard CLI) and pass model as positional
@@ -54,7 +60,7 @@ services:
     entrypoint: ["vllm-omni", "serve"]
     command:
       - "${VOXTRAL_MODEL:-mistralai/Voxtral-4B-TTS-2603}"
-      - "--stage-configs-path=vllm_omni/model_executor/stage_configs/voxtral_tts.yaml"
+      - "--stage-configs-path=/etc/voxtral/voxtral_tts.yaml"
       - "--host=0.0.0.0"
       - "--port=8000"
       - "--gpu-memory-utilization=${VOXTRAL_GPU_UTIL:-0.45}"