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.
260 lines
11 KiB
Bash
Executable File
260 lines
11 KiB
Bash
Executable File
#!/usr/bin/env bats
|
|
# Seam: the frank-small llama.cpp root unit on dankclaw.
|
|
# frank-small is the RTX 3090 endpoint; since 2026-10-06 it serves
|
|
# ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S-mtp (27B; the -mtp file's
|
|
# head is present but NOT drafted — speculation is off) via a CUDA (sm_86)
|
|
# build of llama.cpp master: TWO 131,072-token conversations at Frank's
|
|
# 128k cap (pool 262144 / parallel 2), q8_0 K + q8_0 V (FP8 class), and a
|
|
# vision projector. Frank accepted the tight fit explicitly — the card may
|
|
# land under the old 2-3 GiB floor; the seam pins the arithmetic, the boot
|
|
# log carries the measured free. This seam runs the serve script against a
|
|
# stub engine and asserts on the argv it actually execs, so what is pinned
|
|
# is the command the operator gets.
|
|
|
|
load helpers
|
|
|
|
UNIT="$REPO_ROOT/scripts/frank-small.service"
|
|
SERVE="$REPO_ROOT/scripts/serve-frank-small.sh"
|
|
ENV_FILE="$REPO_ROOT/scripts/frank-small.env"
|
|
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
|
|
ENV_LARGE="$REPO_ROOT/scripts/frank-large.env"
|
|
TARGET_STUB="Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp.gguf"
|
|
# Same basename as the shipped projector: the test env repoints it into $STAGE.
|
|
MM_STUB="mmproj-Qwen3.8-27B-F16.gguf"
|
|
|
|
setup() {
|
|
STAGE="$(mktemp -d)"
|
|
RUNTIME_DIR="$STAGE/llama"
|
|
MODEL_DIR="$STAGE/models"
|
|
mkdir -p "$RUNTIME_DIR/bin" "$MODEL_DIR"
|
|
cat > "$RUNTIME_DIR/bin/llama-server" <<'STUB'
|
|
#!/usr/bin/env bash
|
|
printf '%s\n' "$@"
|
|
STUB
|
|
chmod +x "$RUNTIME_DIR/bin/llama-server" "$RUNTIME_DIR/bin" 2>/dev/null || chmod +x "$RUNTIME_DIR/bin/llama-server"
|
|
touch "$MODEL_DIR/$TARGET_STUB" "$MODEL_DIR/$MM_STUB"
|
|
}
|
|
|
|
teardown() {
|
|
rm -rf "$STAGE"
|
|
}
|
|
|
|
# serve_argv [env-file] — run the serve script and capture the engine's
|
|
# argv, one token per line, in $output.
|
|
serve_argv() {
|
|
local envf="${1:-$STAGE/test.env}"
|
|
local mmproj
|
|
mmproj="$(sed -nE 's/^MMPROJ_FILE=(.+)$/\1/p' "$ENV_FILE")"
|
|
cat > "$envf" <<EOF
|
|
LLAMA_BIN=$RUNTIME_DIR/bin/llama-server
|
|
MODEL_FILE=$MODEL_DIR/$TARGET_STUB
|
|
MMPROJ_FILE=$MODEL_DIR/${mmproj##*/}
|
|
ALIAS=frank-small
|
|
BIND_ADDR=0.0.0.0
|
|
LISTEN_PORT=7771
|
|
CTX_SIZE=$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")
|
|
PARALLEL=$(sed -nE 's/^PARALLEL=([0-9]+)$/\1/p' "$ENV_FILE")
|
|
BATCH_SIZE=$(sed -nE 's/^BATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")
|
|
UBATCH_SIZE=$(sed -nE 's/^UBATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")
|
|
CACHE_TYPE_K=$(sed -nE 's/^CACHE_TYPE_K=(.+)$/\1/p' "$ENV_FILE")
|
|
CACHE_TYPE_V=$(sed -nE 's/^CACHE_TYPE_V=(.+)$/\1/p' "$ENV_FILE")
|
|
NGL=$(sed -nE 's/^NGL=([0-9]+)$/\1/p' "$ENV_FILE")
|
|
EOF
|
|
run env FRANK_SMALL_ENV_FILE="$envf" nvidia-modprobe=true bash "$SERVE"
|
|
}
|
|
|
|
argv_value() {
|
|
grep -A1 -xF -- "$1" <<<"$output" | tail -1
|
|
}
|
|
|
|
@test "frank-small unit, serve script and env exist in scripts/" {
|
|
[ -f "$UNIT" ]
|
|
[ -f "$SERVE" ]
|
|
[ -f "$ENV_FILE" ]
|
|
}
|
|
|
|
@test "frank-small is boot-persistent, self-healing and unprivileged" {
|
|
grep -q '^WantedBy=multi-user.target$' "$UNIT"
|
|
grep -q '^Restart=on-failure$' "$UNIT"
|
|
grep -q '^RestartSec=' "$UNIT"
|
|
grep -q '^User=dank$' "$UNIT"
|
|
grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
|
|
grep -q '^ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-small.sh$' "$UNIT"
|
|
grep -q 'FRANK_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-small.env' "$UNIT"
|
|
}
|
|
|
|
@test "the shipped env points at the llama.cpp runtime and the Swift-1.5-27B IQ3_S-mtp GGUF" {
|
|
grep -qE '^LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server$' "$ENV_FILE"
|
|
grep -qE "^MODEL_FILE=/home/dank/models/Swift15-IQ3S/$TARGET_STUB$" "$ENV_FILE"
|
|
}
|
|
|
|
@test "the deployer gates on exactly the payload paths the env file ships" {
|
|
# Anti-drift: the deploy handler checks files by its own defaults. If
|
|
# those ever differ from what the unit actually loads, a green deploy
|
|
# would be gating on a file nobody reads — and a missing projector would
|
|
# ship a blind endpoint.
|
|
local env_v dep_v path pair
|
|
for pair in "MODEL_FILE LLM_SMALL_MODEL_FILE" "MMPROJ_FILE LLM_SMALL_MMPROJ"; do
|
|
read -r env_v dep_v <<<"$pair"
|
|
path="$(sed -nE "s/^${env_v}=(.+)\$/\1/p" "$ENV_FILE" | tail -1)"
|
|
[ -n "$path" ]
|
|
grep -qF -- "${dep_v}=\"\${${dep_v}:-${path}}\"" "$REMOTE_DEPLOY"
|
|
done
|
|
}
|
|
|
|
@test "the shipped env serves the fleet shape: one conversation at the 128k cap" {
|
|
serve_argv
|
|
[ "$status" -eq 0 ]
|
|
[ "$(argv_value --alias)" = "frank-small" ]
|
|
[ "$(argv_value --port)" = "7771" ]
|
|
[ "$(argv_value --host)" = "0.0.0.0" ]
|
|
[ "$(argv_value --model)" = "$MODEL_DIR/$TARGET_STUB" ]
|
|
[ "$(argv_value --n-gpu-layers)" -gt 0 ]
|
|
# llama.cpp divides --ctx-size across slots and a mamba hybrid cannot
|
|
# share one cache, so the observable contract is the per-slot window.
|
|
# 2026-10-06 (Frank): drop MTP, drop ubatch, and take TWO conversations
|
|
# at 131,072 — pool 262144, parallel 2, per-slot 131072 (the cap).
|
|
[ "$(argv_value --parallel)" -eq 2 ]
|
|
ctx="$(argv_value --ctx-size)"
|
|
par="$(argv_value --parallel)"
|
|
[ $((ctx % par)) -eq 0 ]
|
|
[ $((ctx / par)) -eq 131072 ]
|
|
}
|
|
|
|
@test "the KV contract is q8_0 both halves (FP8 class), flash-attn on" {
|
|
serve_argv
|
|
[ "$status" -eq 0 ]
|
|
# Frank, 2026-10-05 evening: "k/v at FP8" for the Swift-1.5 swap —
|
|
# llama.cpp's FP8 class is q8_0 (1.0625 B/elem => 8.5 effective bits;
|
|
# there is no true fp8 KV dtype). This SUPERSEDES the same-day f16/f16
|
|
# rule written for the Ornith 9B fit. The flag pair is what makes this
|
|
# observable — a build without the FA path silently falls back, so both
|
|
# must appear in the argv the supervisor runs.
|
|
[ "$(argv_value --cache-type-k)" = "q8_0" ]
|
|
[ "$(argv_value --cache-type-v)" = "q8_0" ]
|
|
[ "$(argv_value --flash-attn)" = "on" ]
|
|
}
|
|
|
|
@test "the KV budget fits TWO 128k slots (Frank's tight-fit order) and forbids a third" {
|
|
# Rate, from the Swift-1.5 IQ3_S-mtp GGUF header (read from the Hub
|
|
# file, 2026-10-05): SIXTEEN full-attention layers (block_count 65 = 64
|
|
# real layers + the blk.64 MTP head, full_attention_interval 4) x 4 kv
|
|
# heads x 256 dim x 1.0625 B = 17 KiB/token for K and the same for V
|
|
# => 34 KiB/token at q8_0 (budgeted 37 with slack; f16 would be 64).
|
|
# The non-KV half: IQ3_S-mtp weights 11,561 MiB (12,120,016,896 B) +
|
|
# vision tower ~1.35 GiB (927,607,488 B F16 mmproj at the measured
|
|
# ~1.45x cost law) + compute buffers at ubatch 512 + CUDA graphs + TWO
|
|
# DeltaNet states (~150 MiB each) and NO draft context (speculation is
|
|
# off) => 15 GiB budgeted. 2026-10-06 (Frank): two 131,072 slots are
|
|
# the order — the budget lands AT the card (tight fit, accepted
|
|
# explicitly; the old 2-3 GiB floor is knowingly violated) and a THIRD
|
|
# slot must not fit. Arithmetic, not a boot log: change CTX_SIZE and
|
|
# this bites before the deploy does; the boot's nvidia-smi free is the
|
|
# measured truth.
|
|
ctx="$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
|
|
kv_gib=$((ctx * 37 / 1048576))
|
|
third_slot_kv=$(( (ctx + 131072) * 37 / 1048576 ))
|
|
[ $((kv_gib + 15)) -le 24 ]
|
|
[ $((third_slot_kv + 15)) -gt 24 ]
|
|
}
|
|
|
|
@test "the compute-buffer pair follows the env file and stays self-consistent" {
|
|
# This endpoint ran on llama.cpp's own defaults until 2026-10-03, so the
|
|
# contract is: whatever rung the repo carries is the rung the engine is
|
|
# exec'd with — the number a benchmark attributes a prefill rate to must be
|
|
# a repo value, never an engine default nobody wrote down. Asserted against
|
|
# the env rather than a literal so a retune moves one file, not two.
|
|
local env_batch env_ubatch
|
|
env_batch="$(sed -nE 's/^BATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
|
|
env_ubatch="$(sed -nE 's/^UBATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
|
|
serve_argv
|
|
[ "$status" -eq 0 ]
|
|
[ "$(argv_value --batch-size)" = "$env_batch" ]
|
|
[ "$(argv_value --ubatch-size)" = "$env_ubatch" ]
|
|
# llama.cpp refuses ubatch > batch, so a retune that inverts the pair has
|
|
# to fail here instead of at boot on a live endpoint.
|
|
[ "$env_batch" -ge "$env_ubatch" ]
|
|
|
|
# And an env that names neither flag still ships an explicit pair: the
|
|
# serve script's fallbacks are written-down values, not blanks the engine
|
|
# fills in silently.
|
|
sed -i '/^BATCH_SIZE=/d;/^UBATCH_SIZE=/d' "$STAGE/test.env"
|
|
serve_argv
|
|
[ "$status" -eq 0 ]
|
|
argv_value --batch-size | grep -qE '^[0-9]+$'
|
|
argv_value --ubatch-size | grep -qE '^[0-9]+$'
|
|
}
|
|
|
|
@test "speculation is off: no half spec pair reaches the argv" {
|
|
# Frank, 2026-10-06: drop MTP, skip ngram-mod (on a qwen35 hybrid
|
|
# ngram disables recurrent-state rollback — a rejected draft corrupts
|
|
# the DeltaNet state). The flags move as a set, so the no-spec contract
|
|
# is ABSENCE of both in the argv the supervisor runs, and the env must
|
|
# carry the same contract. The -mtp file's head stays; it is not
|
|
# drafted with. Reference numbers stay in frank-small.env for the day
|
|
# MTP returns (44.8 % acceptance at the recipe temp => 58.9 t/s).
|
|
serve_argv
|
|
[ "$status" -eq 0 ]
|
|
! grep -qxF -- '--spec-type' <<<"$output"
|
|
! grep -qxF -- '--spec-draft-n-max' <<<"$output"
|
|
grep -qE '^SPEC_TYPE=none$' "$ENV_FILE"
|
|
}
|
|
|
|
@test "vision ships by default and MMPROJ_FILE empty opts out of the image path" {
|
|
# The Swift GGUF carries no vision tensors, so the projector argument IS
|
|
# the vision capability: no flag, no eyes.
|
|
serve_argv
|
|
[ "$status" -eq 0 ]
|
|
[ "$(argv_value --mmproj)" = "$MODEL_DIR/$MM_STUB" ]
|
|
|
|
# The documented opt-out must reach the engine as ABSENCE of the flag,
|
|
# not as an argument pointing at an empty string.
|
|
sed -i 's|^MMPROJ_FILE=.*|MMPROJ_FILE=|' "$STAGE/test.env"
|
|
run env FRANK_SMALL_ENV_FILE="$STAGE/test.env" nvidia-modprobe=true bash "$SERVE"
|
|
[ "$status" -eq 0 ]
|
|
! grep -qxF -- '--mmproj' <<<"$output"
|
|
}
|
|
|
|
@test "the fleet reasoning contract survives the reslice to two wide contexts" {
|
|
serve_argv
|
|
[ "$status" -eq 0 ]
|
|
# deepseek format = thinking lands in reasoning_content, the field the
|
|
# harness reads on this endpoint; --jinja is what makes
|
|
# chat_template_kwargs reach the template at all.
|
|
[ "$(argv_value --reasoning-format)" = "deepseek" ]
|
|
argv_value --jinja >/dev/null
|
|
grep -qxF -- '--jinja' <<<"$output"
|
|
}
|
|
|
|
@test "the serve script refuses a missing runtime, GGUF or projector" {
|
|
rm -f "$MODEL_DIR/$MM_STUB"
|
|
serve_argv
|
|
[ "$status" -ne 0 ]
|
|
[[ "$output" == *"frank-small: missing"* ]]
|
|
|
|
rm -f "$RUNTIME_DIR/bin/llama-server"
|
|
serve_argv
|
|
[ "$status" -ne 0 ]
|
|
[[ "$output" == *"frank-small: missing"* ]]
|
|
}
|
|
|
|
@test "the deploy handler gates on binary, GGUF and projector, then MainPID-hardens health" {
|
|
grep -q 'deploy_llm_small' "$REMOTE_DEPLOY"
|
|
grep -q 'LLM_SMALL_RUNTIME' "$REMOTE_DEPLOY"
|
|
grep -q 'LLM_SMALL_MODEL_FILE' "$REMOTE_DEPLOY"
|
|
grep -q 'LLM_SMALL_MMPROJ' "$REMOTE_DEPLOY"
|
|
grep -q 'relink_unit frank-small' "$REMOTE_DEPLOY"
|
|
grep -q 'systemctl enable frank-small.service' "$REMOTE_DEPLOY"
|
|
grep -q '127.0.0.1:7771/health' "$REMOTE_DEPLOY"
|
|
grep -q 'frank-small.service has no MainPID' "$REMOTE_DEPLOY"
|
|
}
|
|
|
|
@test "the two endpoints keep separate ports and the large handler never pkills llama-server" {
|
|
# frank-large's gufo sweep must not take down frank-small, whose
|
|
# process is llama-server on the SAME host since this swap.
|
|
grep -q '^LISTEN_PORT=7771$' "$ENV_FILE"
|
|
local large
|
|
large="$(sed -n '/^deploy_llm_large() {/,/^}/p' "$REMOTE_DEPLOY")"
|
|
! grep -q 'pkill -x llama-server' <<<"$large"
|
|
}
|