Frank
7e6ef1ac99
The VLLM_ATTENTION_BACKEND env var does not exist in this vLLM dev build (warns 'Unknown vLLM environment variable' and is ignored), so the pin landed nowhere and Gemma4's hook force-selected TRITON_ATTN again. Pass --attention-backend TURBOQUANT as a CLI flag instead.
86 lines
3.3 KiB
Bash
Executable File
86 lines
3.3 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Serve google/gemma-4-12B-it-qat-w4a16-ct as frank-small on Dankclaw's RTX
|
|
# 3090 via vLLM (since 2026-09-18), with the google bf16 MTP assistant
|
|
# for speculative decoding.
|
|
#
|
|
# This script is the CONTAINER ENTRYPOINT of the frank-small quadlet: the
|
|
# vllm/vllm-openai image's own entrypoint is `vllm serve`, and the quadlet
|
|
# replaces it with this file (mounted read-only out of the repo checkout) so
|
|
# the flag set stays in git. The image pins the gemma4-unified vLLM build,
|
|
# which is what loads gemma4_unified natively and runs the Gemma 4 MTP path.
|
|
#
|
|
# MTP: the drafter is a separate 4-layer assistant checkpoint in bf16
|
|
# (Google's original gemma-4-12B-it-assistant). It goes in
|
|
# --speculative-config as method "mtp" — vLLM's Gemma 4 MTP path, not a
|
|
# generic draft model. The w4a16-ct re-quant of the assistant was tried
|
|
# first and drafts at acceptance 1.00 (the drafter path does not apply the
|
|
# Marlin kernel to its linears); the bf16 assistant accepts at 2.80.
|
|
#
|
|
# Sampling: greedy by default (fleet contract) via
|
|
# --override-generation-config; clients that send their own temperature get
|
|
# their own, and the harness overrides per model from models.yml.
|
|
#
|
|
# Tunables come from frank-small.env (mounted beside this file by the
|
|
# quadlet) unless FRANK_SMALL_ENV_FILE overrides the path.
|
|
set -euo pipefail
|
|
|
|
ENV_FILE="${FRANK_SMALL_ENV_FILE:-/scripts/frank-small.env}"
|
|
if [[ -f "$ENV_FILE" ]]; then
|
|
set -a
|
|
# shellcheck disable=SC1090
|
|
source "$ENV_FILE"
|
|
set +a
|
|
fi
|
|
|
|
# --- defaults (used when the env file does not set them) -------------------
|
|
: "${MODEL_DIR:=/models/main}"
|
|
: "${DRAFT_DIR:=/models/assistant}"
|
|
: "${ALIAS:=frank-small}"
|
|
: "${BIND_ADDR:=0.0.0.0}"
|
|
: "${LISTEN_PORT:=8000}"
|
|
: "${MAX_MODEL_LEN:=262144}"
|
|
: "${GPU_MEM_UTIL:=0.95}"
|
|
: "${KV_CACHE_DTYPE:=auto}"
|
|
: "${MAX_NUM_SEQS:=16}"
|
|
: "${MAX_NUM_BATCHED_TOKENS:=16384}"
|
|
: "${SPEC_NUM_TOKENS:=4}"
|
|
: "${ATTENTION_BACKEND:=TURBOQUANT}"
|
|
: "${ENFORCE_EAGER:=0}"
|
|
|
|
# Fail loudly rather than half-loading a model into VRAM: a missing file here
|
|
# is a download that has not finished, and the unit's restart policy would
|
|
# otherwise turn that into a crash loop that reads like a runtime fault.
|
|
for path in "$MODEL_DIR/model.safetensors" "$MODEL_DIR/config.json" \
|
|
"$DRAFT_DIR/model.safetensors" "$DRAFT_DIR/config.json"; do
|
|
[[ -e "$path" ]] || { echo "frank-small: missing $path" >&2; exit 1; }
|
|
done
|
|
|
|
SPEC_CONFIG="{\"method\":\"mtp\",\"model\":\"${DRAFT_DIR}\",\"num_speculative_tokens\":${SPEC_NUM_TOKENS}}"
|
|
|
|
VLLM_FLAGS=(
|
|
serve "$MODEL_DIR"
|
|
--served-model-name "$ALIAS"
|
|
--host "$BIND_ADDR"
|
|
--port "$LISTEN_PORT"
|
|
--max-model-len "$MAX_MODEL_LEN"
|
|
--gpu-memory-utilization "$GPU_MEM_UTIL"
|
|
--kv-cache-dtype "$KV_CACHE_DTYPE"
|
|
--max-num-seqs "$MAX_NUM_SEQS"
|
|
--max-num-batched-tokens "$MAX_NUM_BATCHED_TOKENS"
|
|
--attention-backend "$ATTENTION_BACKEND"
|
|
--speculative-config "$SPEC_CONFIG"
|
|
--reasoning-parser gemma4
|
|
--enable-auto-tool-choice
|
|
--tool-call-parser gemma4
|
|
--override-generation-config '{"temperature": 0}'
|
|
)
|
|
# ENFORCE_EAGER=1 skips Inductor/Triton compilation and CUDA graph capture
|
|
# (slower steady-state decode, faster and more robust boot). The 3090 is
|
|
# sm_86 (Ampere) — no native fp8 — so KV stays bf16 and the default
|
|
# graphed path is the right one; the knob is a boot-debugging lever.
|
|
if [[ "$ENFORCE_EAGER" == "1" ]]; then
|
|
VLLM_FLAGS+=(--enforce-eager)
|
|
fi
|
|
|
|
exec vllm "${VLLM_FLAGS[@]}"
|