# mOrpheus stack tunables (irv-ml1). Copy to .env on the host; edit values there.

# GPU pin (UUID). Default = the 3090 (the stabler audio-zoo GPU; A6000 is comfy's + spiky).
#   irv-ml1: 3090 = GPU-12c15b3c-0827-0bab-b0cd-31aaa37a8e72
#            A6000 = GPU-9672f0d5-3caf-b15c-898a-cd9d653c654b
MORPHEUS_GPU_UUID=GPU-12c15b3c-0827-0bab-b0cd-31aaa37a8e72

# Weights (stage once; not in git). mOrpheus = LlamaForCausalLM 3.3B bf16 (6.6GB).
MORPHEUS_MODEL_DIR=/home/lkraven/morpheus/models/mOrpheus
SNAC_DIR=/home/lkraven/morpheus/models/snac_24khz

# Engine. bf16 REQUIRED — FP8 destroys audio-token generation on this model (0 valid SNAC
#   frames even at greedy). bf16 weights ~6.6GB; --enforce-eager (in compose) skips CUDA-
#   graph capture so it fits the shared 3090. util 0.32 (~7.7GB of the 24GB card); raise if
#   you free the 3090, lower only if you can (bf16 weights alone are 6.6GB => >=~0.30 floor).
MORPHEUS_GPU_UTIL=0.32
MORPHEUS_MAX_LEN=4096
MORPHEUS_MAX_SEQS=8

# TTS endpoint (host port). Public /tts + /docs live here.
MORPHEUS_TTS_PORT=8299
MORPHEUS_DEFAULT_VOICE=baddy
MORPHEUS_VOICES=baddy