# gen-seat tunables — fleet `gen` seat (ana-ml2 GPU 0, :8015). Edit here, never commit.
GEN_IMAGE=vllm/vllm-openai:nightly-311b3513af33bc29b4acb2fde2e9313e5e9966a0
API_KEY=
GEN_GPU_ID=0

GEN_CONTAINER_NAME=vllm-gen
GEN_PORT=8015
GEN_SERVED_NAME=qwen3.8-27b-uncensored
GEN_SERVED_NAME_THINK=qwen3.8-27b-uncensored-thinking
GEN_MODEL=/tank/aimodels/qwen38-27b-uncensored-nvfp4-mixed
GEN_QUANT=compressed-tensors
# 0.43 not 0.45: the mixed build's weights are 5.2 GB smaller, and at 0.45 the
# seat absorbed that slack as extra KV, leaving meromero-charrp 0.18 GiB short
# of its 0.52 budget on the shared GPU0 (it crash-looped). 0.43 still gives gen
# 422K tokens of KV = 1.6x its 262K context. Both seats: 89.8/97.9 GB.
GEN_GPU_MEM_UTIL=0.43
GEN_MAX_MODEL_LEN=262144
GEN_MAX_NUM_SEQS=16
GEN_KV_CACHE_DTYPE=fp8
GEN_REASONING_PARSER=qwen3
GEN_SPEC_METHOD=qwen3_5_mtp
# 3 is the measured optimum, not a default: swept n=2/3/4/5 on this seat ->
# 77.1 / 80.1 / 78.7 / 75.9 tok/s. Higher n trades acceptance for draft width
# and loses. Do not re-chase.
GEN_SPEC_TOKENS=3