Frank
812d9ebff5
CTX 262144 / PARALLEL 2 = two 131,072 conversations; SPEC_TYPE=none strips both speculative flags in the serve script (ngram-mod skipped on purpose — on a qwen35 hybrid it disables recurrent-state rollback); ubatch 1024->512 claws back ~0.3 GiB. Budget: non-KV ~15.5 GiB + two q8_0 slots 8,704 MiB lands AT the card — the 2-3 GiB floor is knowingly violated by explicit order; nvidia-smi free at boot is the measured truth. Seam retargeted: shape (2 slots, 131072/slot), budget (two fit, three don't), spec-off (absence of both flags), unit Description.
120 lines
5.2 KiB
Bash
Executable File
120 lines
5.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Serve ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF (IQ3_S **-mtp**) as
|
|
# frank-small on Dankclaw's RTX 3090 via llama.cpp (master build, CUDA
|
|
# sm_86).
|
|
#
|
|
# 2026-10-06 (Frank): the 128k cap keeps the per-conversation window but
|
|
# the pool doubles to TWO 131,072 conversations (262144 / 2), speculative
|
|
# decoding is OFF (no draft-mtp; ngram skipped — on a qwen35 hybrid it
|
|
# disables recurrent-state rollback), and ubatch drops to 512. Frank
|
|
# accepted the tight fit explicitly (the 2-3 GiB floor is knowingly
|
|
# violated; frank-small.env carries the arithmetic). The q8_0 KV contract
|
|
# (FP8 class) is unchanged; the per-tensor flags stay explicit either way.
|
|
#
|
|
# Architecture: qwen35 hybrid — 64 real layers, 16 full-attention + 48
|
|
# Gated DeltaNet (full_attention_interval 4), native 262144 window, plus
|
|
# the blk.64 MTP head (nextn_predict_layers=1). KV lives only in the 16
|
|
# attention layers (34 KiB/token at q8_0); the DeltaNet state is per-slot
|
|
# fixed size. Vision comes from the projector file (the GGUF carries no
|
|
# vision tensors; unsloth's mmproj built from the shared Qwen3.8-27B base —
|
|
# proven byte-identical to Swift's own tower, see download-frank-small.sh),
|
|
# 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}"
|
|
: "${MODEL_FILE:=/home/dank/models/Swift15-IQ3S/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp.gguf}"
|
|
: "${ALIAS:=frank-small}"
|
|
: "${BIND_ADDR:=0.0.0.0}"
|
|
: "${LISTEN_PORT:=7771}"
|
|
# ctx-size is the POOL llama.cpp divides across slots: 262144 / 2 gives
|
|
# TWO 131,072 conversations — Frank's 128k cap each. 2026-10-06 (Frank):
|
|
# drop MTP, drop ubatch to 512, take two slots; the fit is tight by his
|
|
# explicit order (frank-small.env carries the arithmetic and the floor
|
|
# violation).
|
|
: "${CTX_SIZE:=262144}"
|
|
: "${PARALLEL:=2}"
|
|
# Compute-buffer geometry. Ubatch is a prefill knob (decode never moves).
|
|
# Frank's 2026-10-06 tight-fit order ships 4096/512 (claws back ~0.3 GiB
|
|
# toward the second slot); ubatch 1024 is the first A/B back if a future
|
|
# boot lands with headroom (a miss fails loud at graph capture). The
|
|
# logical batch is VRAM- and throughput-neutral at a fixed ubatch.
|
|
: "${BATCH_SIZE:=4096}"
|
|
: "${UBATCH_SIZE:=512}"
|
|
# KV at FP8 class = q8_0 on llama.cpp (1.0625 B/elem => 8.5 effective bits;
|
|
# there is no true fp8 KV dtype). Explicit either way so the contract is
|
|
# visible in the argv.
|
|
: "${CACHE_TYPE_K:=q8_0}"
|
|
: "${CACHE_TYPE_V:=q8_0}"
|
|
# Speculative decoding is OFF by default (Frank, 2026-10-06): SPEC_TYPE
|
|
# none strips BOTH speculative flags (flags move as a set). Setting a
|
|
# drafter here re-enables the pair — draft-mtp needs the head that is IN
|
|
# the -mtp GGUF.
|
|
: "${SPEC_TYPE:=none}"
|
|
: "${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.
|
|
: "${MMPROJ_FILE=/home/dank/models/Swift15-IQ3S/mmproj-Qwen3.8-27B-F16.gguf}"
|
|
|
|
# Fail loudly rather than half-loading: a missing file is a download that
|
|
# has not finished, and Restart=always would turn it into a crash loop that
|
|
# reads like a runtime fault.
|
|
for path in "$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
|
|
|
|
# Speculative flags move as a set: they reach the argv ONLY when a drafter
|
|
# is named. SPEC_TYPE=none (the shipped contract) strips both — a no-spec
|
|
# baseline must not carry half a spec pair.
|
|
if [[ -n "$SPEC_TYPE" && "$SPEC_TYPE" != "none" ]]; then
|
|
EXTRA_ARGS+=(--spec-type "$SPEC_TYPE" --spec-draft-n-max "$SPEC_DRAFT_N_MAX")
|
|
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
|
|
|
|
# Flash attention stays pinned on: it is REQUIRED for quantized V (q8_0),
|
|
# and the build carries GGML_CUDA_FA_ALL_QUANTS=ON (since 2026-09-17), so
|
|
# the q8_0 KV contract in frank-small.env is a real path — without this
|
|
# flag or that build option the engine silently falls back and the
|
|
# contract becomes a lie.
|
|
ARGS=(
|
|
--model "$MODEL_FILE"
|
|
--alias "$ALIAS"
|
|
--host "$BIND_ADDR"
|
|
--port "$LISTEN_PORT"
|
|
--ctx-size "$CTX_SIZE"
|
|
--parallel "$PARALLEL"
|
|
--batch-size "$BATCH_SIZE"
|
|
--ubatch-size "$UBATCH_SIZE"
|
|
--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[@]}"}
|