[infer]
socket = "/tmp/infer.sock"
model = "some-model"

[slots]
main = 2
background = 3

[expect]
template_sha256 = "000102030405060708090a0b0c0d0e0f101112131415161718191a1b1c1d1e1f"
n_ctx = 4096
slots = 4

[sampling]
temperature = 0.2
top_p = 0.9
top_k = 40

[limits]
poll_ms = 50
busy_wait_ms = 200
load_wait_ms = 300
idle_grace_ms = 150
liveness_ms = 100
thinking_cap = 20
thinking_overrun = 10
max_tokens = 512
queue_len = 1
retry_attempts = 2
retry_backoff_ms = [10]
retry_window_ms = 1000