Frank
a02850203d
CTX_SIZE 589824 / PARALLEL 3 -> three independent 196,608-token conversations (a mamba hybrid cannot share one KV cache, so per-slot window = pool/slots; 3 x 262,144 would need 18.4 GiB of KV alone and busts the card). Vision comes back via bartowski's mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf (918,166,048 B, sha256 ff348f31..., fetched + verified by scripts/download-frank-small.sh): the Q5_K_M GGUF ships no v.* tensors, so --mmproj IS the image path. MMPROJ_FILE without a colon default so an explicit empty value is a real text-only opt-out, and the deployer now gates on the projector exactly as the serve script does. Budget is measured, not guessed: the 2 x 262,144 shape used 20,190/24,576 MiB, which prices non-KV cost at 7,390 MiB. Three slots + projector land near 22.5 GiB, i.e. ~2 GiB spare - the bottom of the requested band, to be confirmed by measurement and laddered if it lands outside 2-3 GiB.
88 lines
3.6 KiB
Bash
Executable File
88 lines
3.6 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Serve bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF (Q5_K_M) as frank-small on
|
|
# Dankclaw's RTX 3090 via llama.cpp (master build, CUDA sm_86).
|
|
#
|
|
# 2026-10-01 night (Frank): swapped from SGLang + INT8-W8A16-AutoRound
|
|
# safetensors to the llama.cpp GGUF path, because llama.cpp is the only
|
|
# runtime on this host that can serve the MiMo qwen35 hybrid with
|
|
# ASYMMETRIC KV: --cache-type-k f16 (unquantized keys) + --cache-type-v
|
|
# q8_0 (quantized values), which is Frank's explicit KV contract for this
|
|
# endpoint. SGLang's --kv-cache-dtype only moves K and V together.
|
|
#
|
|
# Architecture: qwen3_5 hybrid — 32 layers, 8 full-attention + 24 Gated
|
|
# DeltaNet, native 262144 window. KV lives only in the 8 attention layers;
|
|
# the DeltaNet state is per-slot fixed size. Vision comes from the repo's
|
|
# separate projector (the Q5_K_M GGUF carries no `v.*` tensors at all), so
|
|
# --mmproj is what gives this endpoint eyes; MMPROJ_FILE="" is the documented
|
|
# text-only opt-out.
|
|
#
|
|
# Sampling: llama.cpp takes it per request (the fleet harness sends its
|
|
# recipe from models.yml); greedy is the harness default.
|
|
#
|
|
# Tunables come from frank-small.env unless FRANK_SMALL_ENV_FILE overrides.
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
|
ENV_FILE="${FRANK_SMALL_ENV_FILE:-$SCRIPT_DIR/frank-small.env}"
|
|
if [[ -f "$ENV_FILE" ]]; then
|
|
set -a
|
|
# shellcheck disable=SC1090
|
|
source "$ENV_FILE"
|
|
set +a
|
|
fi
|
|
|
|
# --- defaults (used when the env file does not set them) -------------------
|
|
: "${LLAMA_BIN:=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
|
|
: "${MODEL_FILE:=/home/dank/models/MiMo-Q5KM/MiMo-V2.6-Distill-Qwen-9B-Q5_K_M.gguf}"
|
|
: "${ALIAS:=frank-small}"
|
|
: "${BIND_ADDR:=0.0.0.0}"
|
|
: "${LISTEN_PORT:=7771}"
|
|
# ctx-size is the POOL llama.cpp divides across slots: 589824 / 3 gives
|
|
# 196608 per slot — three independent conversations, each with a 192k window
|
|
# (the native 262144 no longer fits three times on a 24 GiB card; see
|
|
# frank-small.env for the arithmetic that lands ~2.5 GiB of card free).
|
|
: "${CTX_SIZE:=589824}"
|
|
: "${PARALLEL:=3}"
|
|
: "${CACHE_TYPE_K:=f16}"
|
|
: "${CACHE_TYPE_V:=q8_0}"
|
|
: "${NGL:=99}"
|
|
# Vision projector. No colon on purpose: an explicitly empty value means
|
|
# "text-only, on purpose" and must NOT be replaced by the default path.
|
|
: "${MMPROJ_FILE=/home/dank/models/MiMo-Q5KM/mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf}"
|
|
|
|
# Fail loudly rather than half-loading: a missing file is a download that
|
|
# has not finished, and Restart=always would turn it into a crash loop that
|
|
# reads like a runtime fault.
|
|
for path in "$LLAMA_BIN" "$MODEL_FILE"; do
|
|
[[ -e "$path" ]] || { echo "frank-small: missing $path" >&2; exit 1; }
|
|
done
|
|
EXTRA_ARGS=()
|
|
if [[ -n "$MMPROJ_FILE" ]]; then
|
|
[[ -e "$MMPROJ_FILE" ]] || { echo "frank-small: missing $MMPROJ_FILE" >&2; exit 1; }
|
|
EXTRA_ARGS+=(--mmproj "$MMPROJ_FILE")
|
|
fi
|
|
|
|
# The UVM device node is created lazily by nvidia-modprobe on the first CUDA
|
|
# open after boot; make sure it exists before the server needs it.
|
|
nvidia-modprobe -u -c=0 2>/dev/null || true
|
|
|
|
# q8_0 on V REQUIRES flash attention (the quantized-value kernels only exist
|
|
# on the FA path); an FA-less build silently falls back and the KV contract
|
|
# in frank-small.env becomes a lie, so pin the flag pair here.
|
|
ARGS=(
|
|
--model "$MODEL_FILE"
|
|
--alias "$ALIAS"
|
|
--host "$BIND_ADDR"
|
|
--port "$LISTEN_PORT"
|
|
--ctx-size "$CTX_SIZE"
|
|
--parallel "$PARALLEL"
|
|
--n-gpu-layers "$NGL"
|
|
--flash-attn on
|
|
--cache-type-k "$CACHE_TYPE_K"
|
|
--cache-type-v "$CACHE_TYPE_V"
|
|
--jinja
|
|
--reasoning auto
|
|
--reasoning-format deepseek
|
|
)
|
|
exec "$LLAMA_BIN" "${ARGS[@]}" ${EXTRA_ARGS[@]+"${EXTRA_ARGS[@]}"}
|