#!/usr/bin/env bash
# Serve Avesed/Qwen3.6-35B-A3B-INT8-W8A8 via vLLM on Dankclaw (Strix Halo).
#
# Runs the ROCm vLLM build in /home/dank/vllm-venv. The model is a
# compressed-tensors INT8 W8A8 quant (MoE, 35B total / 3B active). Full
# 262144 context, unquantized KV cache, 4 concurrent sequences, ngram
# speculative decoding.
#
# Tunables come from frank-default-small.env in this directory unless
# FRANK_SMALL_ENV_FILE overrides that path.
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ENV_FILE="${FRANK_SMALL_ENV_FILE:-$SCRIPT_DIR/frank-default-small.env}"
if [[ -f "$ENV_FILE" ]]; then
    set -a
    # shellcheck disable=SC1090
    source "$ENV_FILE"
    set +a
fi

# --- defaults (used when the env file does not set them) -------------------
: "${VLLM_BIN:=/home/dank/vllm-venv/bin/vllm}"
: "${MODEL:=Avesed/Qwen3.6-35B-A3B-INT8-W8A8}"
: "${ALIAS:=frank-default-small}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=52625}"
: "${MAX_MODEL_LEN:=262144}"
: "${KV_CACHE_DTYPE:=auto}"
: "${MAX_NUM_SEQS:=4}"
: "${MAX_NUM_BATCHED_TOKENS:=16384}"
: "${GPU_MEMORY_UTILIZATION:=0.92}"
: "${NGRAM_LOOKUP_MAX:=5}"
: "${NGRAM_LOOKUP_MIN:=1}"
: "${NUM_SPEC_TOKENS:=5}"

if [[ ! -x "$VLLM_BIN" ]]; then
    echo "missing vllm binary: $VLLM_BIN" >&2
    exit 1
fi

exec "$VLLM_BIN" serve "$MODEL" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT" \
    --served-model-name "$ALIAS" \
    --max-model-len "$MAX_MODEL_LEN" \
    --kv-cache-dtype "$KV_CACHE_DTYPE" \
    --max-num-seqs "$MAX_NUM_SEQS" \
    --max-num-batched-tokens "$MAX_NUM_BATCHED_TOKENS" \
    --gpu-memory-utilization "$GPU_MEMORY_UTILIZATION" \
    --speculative-config "{\"method\":\"ngram\",\"prompt_lookup_max\":$NGRAM_LOOKUP_MAX,\"prompt_lookup_min\":$NGRAM_LOOKUP_MIN,\"num_speculative_tokens\":$NUM_SPEC_TOKENS}" \
    --reasoning-parser qwen3 \
    --trust-remote-code