# coder-seat tunables (nh3-ml1). Copy to `.env` on the server.

# Same vLLM as fv-ml1's seat, so the move changes only the GPU.
VLLM_VERSION=v0.24.0

# Same port as on fv-ml1, so the gateway entry changes only its host.
CODER_PORT=8020

CODER_MODEL=Qwen/Qwen2.5-Coder-1.5B
CODER_REVISION=df3ce67c0e24480f20468b6ef2894622d69eb73b
CODER_SERVED_NAME=qwen2.5-coder-1.5b
CODER_MAX_MODEL_LEN=16384
CODER_MAX_NUM_SEQS=32
CODER_KV_CACHE_DTYPE=fp8

# Fraction of the Ada's TOTAL 16,380 MiB: 0.33 ≈ 5.4 GB, the same absolute
# budget fv-ml1 gave it (0.055 of 97,887 MiB). Weights ~3.1 GB bf16; fp8 KV is
# ~14 KB/token, so the rest holds far more than one 16k sequence. vLLM checks
# it against FREE memory at start; TEI holds ~2.6 GB of the card.
CODER_GPU_MEM_UTIL=0.33

# Matches fv-ml1: no key (internal network; the gateway fronts it).
API_KEY=