##
## vLLM engine configuration — smol135 (CPU smoke test)
##
## Consumed by `vllm serve --config` (see vllm-model@.container). Each key is a
## long CLI flag with the leading `--` stripped; store-true flags (e.g.
## --enforce-eager) become `true`.
##
## Installed to /etc/quadlets/vllm/models/smol135.yaml and mounted read-only into
## the container at /etc/vllm/config.yaml.
##

# Ultra-light model of a DIFFERENT architecture (Llama vs Qwen2) so the swap is
# genuinely exercised. No tool-call parser (SmolLM has no tool template).
model: HuggingFaceTB/SmolLM2-135M-Instruct
served-model-name: smol135
dtype: bfloat16
max-model-len: 4096
max-num-seqs: 4

##
## Per-instance fixed host-loopback port for the smol135 model.
##
## Referenced by llmsnap's per-model
## `proxy: http://127.0.0.1:5802` in config.yaml (llmsnap runs Network=host and
## reaches the model here). Each model gets its OWN port so two models can be
## resident at once (GPU sleep mode). Keep it in sync with config.yaml.
##
port: 5802

# --enforce-eager: this CPU image's torch inductor JIT fails at warmup; eager
# mode skips it (fine for a smoke test).
enforce-eager: true