# zonos-engine tunables — ZONOS2 native TTS engine (:1920, irv-ml1 3090).
# Copy to .env on the host. These feed both zonos2-server.sh (native) and the
# eventual container CMD/compose. Values captured from the live process 2026-07-16.

# Upstream repo (github.com/Zyphra/Zonos2) commit to pin — reproducibility.
ZONOS_COMMIT=194c0a3
ZONOS_MODEL=Zyphra/ZONOS2

# Endpoint
ZONOS_PORT=1920

# GPU — 3090 (irv-ml1 device 0). Operator 2026-07-16: keep OFF the A6000 (it OOMs
# under ComfyUI load). Container: NVIDIA_VISIBLE_DEVICES=0; native: the 3090 UUID.
ZONOS_ENGINE_GPU_ID=0

# Serving/perf flags (paged KV + cuda graphs; tuned to co-exist on the packed 3090).
ZONOS_CUDA_GRAPH_MAX_BS=1
ZONOS_NUM_PAGES=16384
ZONOS_MAX_RUNNING_REQUESTS=2
ZONOS_MEMORY_RATIO=0.3

# HF weights cache (~15 GB, models--Zyphra--ZONOS2) — MOUNT, do not bake into the image.
HF_HOME=/home/lkraven/.cache/huggingface