Frank
26f6f82c98
- AGENTS.md: fleet table + frank-primary section back to qwen FP8 + MTP4 (37.4-40.6 tok/s, 54% acceptance); GLM runbook moved to the retired index. - runbook: RETIRED verdict — DFlash2 drafter served and drafted but acceptance pinned 1.00-1.38 on every text class including verbatim repetition (mis-wired aux capture, not a weak drafter); 5x slower than baseline at ~1.2 acceptance. - log.md: 2026-10-01 rollback entry. - deploy-remote.sh: LLM_PRIMARY_CONTAINER back to frank-primary-qwen; glm-probe joins the legacy sweep list. - frank_primary_unit.bats: re-pinned to the qwen shape — KV qualification law (7.2 GiB/rank, 3.65x concurrency; 9/16 GiB OOM), fp8 q8/q8 KV PRESENT, MTP4 PRESENT (3.1-3.4x over the 12.11 no-spec baseline), no tool dialect, automatic offload. The old 'MTP buys zero' law carried the prefetch tax and is retired.
244 lines
12 KiB
Bash
Executable File
244 lines
12 KiB
Bash
Executable File
#!/usr/bin/env bats
|
|
# Seam: frank-primary — the Dankserver LLM endpoint on :7770.
|
|
#
|
|
# This file asserts the tcclaviger RDNA4 vLLM ROOT-UNIT shape (the
|
|
# 2026-10-01 rollback to Qwen3.8-Flash-Next-Uncensored-FP8 + MTP4, which
|
|
# reversed the failed GLM/DFlash2 experiment): the serve script drives
|
|
# `podman run` DIRECTLY (the image entrypoint execs `vllm serve`), with every
|
|
# engine flag qualified by boot probe and carried in the repo env file. The
|
|
# seam pins what the flags alone do not say: the KV qualification law
|
|
# (7.2 GiB/rank boots at 729,545 tokens / 3.65x concurrency; 9 GiB and 16 GiB
|
|
# both OOM the worker — 4 full-length 200k contexts do NOT fit), the fp8-KV
|
|
# qualification (e4m3 for BOTH K and V — the stock flag quantizes them
|
|
# together), the automatic-offload law (the fork plans the tiered-expert
|
|
# offload itself; no flag exists to set), the self-healing law (the run
|
|
# returns before the engine is up, so the serve script must wait on the
|
|
# container for Restart=on-failure to mean anything), the memlock law that
|
|
# makes the pinned host rows legal, the deployer's image/payload gates with
|
|
# the false-green MainPID check, and the measured laws: expert prefetch
|
|
# ABSENT (36% precision, costs ~40-51% decode — deleting the flag moved
|
|
# decode 26.8 -> 40.6 tok/s), MTP4 PRESENT (37.4-40.6 tok/s at 54% acceptance
|
|
# vs the 12.11 tok/s no-spec baseline; the earlier "MTP buys zero" reading
|
|
# carried the prefetch tax), and NO tool dialect (the GLM era added
|
|
# --enable-auto-tool-choice; the 2339fae trio does not serve tools).
|
|
|
|
load helpers
|
|
|
|
UNIT="$REPO_ROOT/scripts/frank-primary.service"
|
|
SERVE="$REPO_ROOT/scripts/serve-frank-primary.sh"
|
|
ENV_FILE="$REPO_ROOT/scripts/frank-primary.env"
|
|
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
|
|
DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"
|
|
|
|
@test "frank-primary unit, serve script and env exist in scripts/" {
|
|
[ -f "$UNIT" ]
|
|
[ -x "$SERVE" ]
|
|
[ -f "$ENV_FILE" ]
|
|
}
|
|
|
|
@test "frank-primary is boot-persistent, self-healing and unprivileged" {
|
|
# Root unit parity with frank-large/frank-small: enable is the [Install]
|
|
# section, the restart policy survives a crash, and the tiered-expert
|
|
# pin needs an unbounded memlock (a root unit grants it via PID1; the
|
|
# dank session's own hard limit is 8 MiB and cannot be raised without
|
|
# restarting user@1000.service).
|
|
grep -q '^WantedBy=multi-user.target$' "$UNIT"
|
|
grep -q '^Restart=on-failure$' "$UNIT"
|
|
grep -q '^RestartSec=' "$UNIT"
|
|
grep -q '^User=dank$' "$UNIT"
|
|
grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
|
|
}
|
|
|
|
@test "frank-primary runs the repo's own serve script with the repo's env" {
|
|
grep -q '^ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-primary.sh$' "$UNIT"
|
|
grep -q 'FRANK_PRIMARY_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-primary.env' "$UNIT"
|
|
}
|
|
|
|
@test "the unit stops the container child explicitly" {
|
|
# The serve script blocks on podman wait, which cannot stop the
|
|
# container child; systemd stop goes through ExecStop or the engine
|
|
# outlives the unit and holds both GPUs. The container name must match
|
|
# the env file's identity.
|
|
grep -q '^ExecStop=/usr/bin/podman stop' "$UNIT"
|
|
grep -q 'frank-primary-qwen' "$UNIT"
|
|
grep -q '^FRANK_PRIMARY_CONTAINER=frank-primary-qwen$' "$ENV_FILE"
|
|
}
|
|
|
|
@test "the serve shape is direct podman run, not a launcher or shim" {
|
|
# The tcclaviger stack is fully expressed by flags; the R9V launcher,
|
|
# docker->podman shim and setup-state layering are the RETIRED shape.
|
|
grep -q 'podman run' "$SERVE"
|
|
! grep -q 'launch.sh' "$SERVE"
|
|
! grep -q 'podman-shim' "$SERVE"
|
|
! grep -q 'R9V_STATE_FILE' "$SERVE"
|
|
! grep -q -- '--model-draft' "$SERVE"
|
|
! grep -q -- '--spec-type' "$SERVE"
|
|
}
|
|
|
|
@test "the qualified engine shape is in the env file" {
|
|
# 2026-09-29 boot probe: 200,000 x 3 seqs at fp8 KV, util 0.98, KV_BYTES
|
|
# 7.2 GiB PER RANK boots at "GPU KV cache size: 729,545 tokens" and
|
|
# reports max concurrency 3.65x for 200,000-token requests. KV_BYTES is
|
|
# PER RANK — sizing it to the global requirement OOMs the worker
|
|
# (measured twice: 16 GiB and 9 GiB both die with ~7.5 GiB free). So 4
|
|
# full-length 200k contexts do NOT fit: four clients share the ~730k
|
|
# token pool and each runs below 200k when all are deep.
|
|
grep -q '^FRANK_PRIMARY_MAXLEN=200000$' "$ENV_FILE"
|
|
grep -q '^FRANK_PRIMARY_SEQS=3$' "$ENV_FILE"
|
|
grep -q '^FRANK_PRIMARY_UTIL=0.98$' "$ENV_FILE"
|
|
grep -q '^FRANK_PRIMARY_KV_BYTES=7730934784$' "$ENV_FILE"
|
|
grep -q '^FRANK_PRIMARY_KV_DTYPE=fp8$' "$ENV_FILE"
|
|
grep -q '^FRANK_PRIMARY_SPEC=4$' "$ENV_FILE"
|
|
grep -q '^FRANK_PRIMARY_MODEL_SHARDS=131$' "$ENV_FILE"
|
|
}
|
|
|
|
@test "the serve script wires the engine flags from the env" {
|
|
grep -q -- '--max-num-seqs "$FRANK_PRIMARY_SEQS"' "$SERVE"
|
|
grep -q -- '--max-model-len "$FRANK_PRIMARY_MAXLEN"' "$SERVE"
|
|
grep -q -- '--kv-cache-memory-bytes "$FRANK_PRIMARY_KV_BYTES"' "$SERVE"
|
|
grep -q -- '--kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE"' "$SERVE"
|
|
grep -q -- '--speculative-config \"{\\\"method\\\":\\\"mtp\\\",\\\"num_speculative_tokens\\\":\$FRANK_PRIMARY_SPEC}\"' "$SERVE"
|
|
grep -q -- '--tensor-parallel-size 2' "$SERVE"
|
|
grep -q -- '--enable-prefix-caching' "$SERVE"
|
|
grep -q -- '--trust-remote-code' "$SERVE"
|
|
}
|
|
|
|
@test "the endpoint serves NO tool dialect — tool agents route elsewhere" {
|
|
# The 2339fae trio does NOT wire --enable-auto-tool-choice /
|
|
# --tool-call-parser (the GLM era added glm47 dialect flags; the rollback
|
|
# dropped them). tool_choice "auto" gets a 400 here — tool-using agents
|
|
# must route at frank-small or frank-large until a parser is qualified
|
|
# for this arm (a behavior change beyond the rollback, not a silent fix).
|
|
! grep -q -- '--enable-auto-tool-choice' "$SERVE"
|
|
! grep -q -- '--tool-call-parser' "$SERVE"
|
|
}
|
|
|
|
@test "expert offload is AUTOMATIC — the payload cannot fit VRAM and no flag sets it" {
|
|
# ~86 GiB/rank of FP8 trunk against 32 GiB of VRAM: the fork's tiered-
|
|
# expert planner moves the overflow to pinned host rows by itself (the
|
|
# arena 6,574 slots x 2.344 MiB plus host rows). There is no
|
|
# --enable-expert-offload flag in this arm; the legality of the pin is
|
|
# the unit's unbounded LimitMEMLOCK.
|
|
! grep -q -- '--enable-expert-offload' "$SERVE"
|
|
! grep -q -- '--expert-precise-memory' "$SERVE"
|
|
grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
|
|
grep -q -- '--ipc=host --ulimit memlock=-1:-1' "$SERVE"
|
|
}
|
|
|
|
@test "MTP4 spec decode is PRESENT BY MEASUREMENT" {
|
|
# 2026-09-29 campaign at prefetch OFF: MTP4 measures 40.57/37.44/37.57
|
|
# tok/s (166/1087/4064 prompt tokens) at 54% acceptance vs the no-spec
|
|
# baseline 12.11 tok/s (dead flat, expert-gather bound) — a measured
|
|
# 3.1-3.4x win. MTP3 measured 24.4 (still 2x baseline), MTP6 collapses
|
|
# (17.4% acceptance). The earlier "MTP buys zero decode" reading carried
|
|
# the prefetch tax and is retired with it. ngram-mod never booted on this
|
|
# model (fork bug: PLE inputs prepared only on the MTP path).
|
|
grep -q '^FRANK_PRIMARY_SPEC=4$' "$ENV_FILE"
|
|
grep -q -- '--speculative-config' "$SERVE"
|
|
}
|
|
|
|
@test "fp8 KV is PRESENT — q8/q8 qualified on this arm" {
|
|
# --kv-cache-dtype fp8 is e4m3 for BOTH K and V (the stock flag quantizes
|
|
# them together; a V-only quant needs a fork patch). The GLM-era MLA
|
|
# concern (sparse-triton MLA decode path refusing fp8 KV) does not apply
|
|
# to this arm: qwen's attention path accepted the dtype and a completion
|
|
# probe qualified it 2026-09-29.
|
|
grep -q '^FRANK_PRIMARY_KV_DTYPE=fp8$' "$ENV_FILE"
|
|
grep -q -- '--kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE"' "$SERVE"
|
|
}
|
|
|
|
@test "expert prefetch is absent BY LAW, not by omission" {
|
|
# Telemetry (2026-09-29): the prefetcher served 13,369 of 36,720
|
|
# prefetched slabs (36% precision) — roughly half the gather traffic was
|
|
# waste, and the "savings" would have been installs anyway. Deleting the
|
|
# flag moved decode 26.8 -> 40.6 tok/s. Any future flag must come with a
|
|
# fresh A/B, so the serve script must NOT wire it unconditionally.
|
|
! grep -q -- '--expert-prefetch' "$SERVE"
|
|
! grep -q 'expert_prefetch' "$ENV_FILE"
|
|
grep -q 'PREFETCH IS ABSENT BY LAW' "$ENV_FILE"
|
|
}
|
|
|
|
@test "TunableOp stays off" {
|
|
# CLAV_TUNABLEOP_SWEEP silently skips under expert offload unless
|
|
# CLAV_TUNABLEOP_WITH_OFFLOAD=1, and forcing it corrupts numerics
|
|
# (repetition loops, early halts, invalid measurements).
|
|
! grep -q 'TUNABLEOP' "$ENV_FILE"
|
|
! grep -q 'TUNABLEOP' "$SERVE"
|
|
}
|
|
|
|
@test "the serve script gates the digest-pinned image and the payload" {
|
|
# The image is pinned by OCI manifest digest (the floating :latest moved
|
|
# once already). The payload gate checks config.json and the exact shard
|
|
# count from the env — a missing shard means a guaranteed long-timeout
|
|
# boot instead of a fast failure.
|
|
grep -q 'FRANK_PRIMARY_IMAGE' "$SERVE"
|
|
grep -q 'RepoDigests' "$SERVE"
|
|
grep -q 'FRANK_PRIMARY_MODEL_SHARDS' "$SERVE"
|
|
grep -q 'config.json' "$SERVE"
|
|
grep -q '/dev/kfd' "$SERVE"
|
|
grep -q -- '--device /dev/dri' "$SERVE"
|
|
! grep -q 'tcclaviger/vllm:latest' "$ENV_FILE"
|
|
}
|
|
|
|
@test "the serve script clears stale containers and self-heals via podman wait" {
|
|
# A crashed unit can leave the container name registered forever after;
|
|
# the legacy identities (the retired R9V container and the ad hoc
|
|
# experiment container) hold the same GPUs and die here too. Then block
|
|
# on the container so a crash is a nonzero ExecStart.
|
|
grep -q 'FRANK_PRIMARY_LEGACY_CONTAINERS' "$ENV_FILE"
|
|
grep -q 'frank-primary-r9v' "$ENV_FILE"
|
|
grep -q 'qwen-fp8' "$ENV_FILE"
|
|
grep -q 'exec podman wait "$FRANK_PRIMARY_CONTAINER"' "$SERVE"
|
|
}
|
|
|
|
@test "frank-primary holds the single fleet port under its own alias" {
|
|
# The scratch identity (qwen3.8-flash-next on :7773) must never leak
|
|
# into production: LAN publish of :7770, the harness's model id.
|
|
grep -q '^FRANK_PRIMARY_PUBLISH=7770:7770$' "$ENV_FILE"
|
|
grep -q '^FRANK_PRIMARY_SERVED_NAME=frank-primary$' "$ENV_FILE"
|
|
}
|
|
|
|
@test "the model id matches the payload's served alias wiring" {
|
|
# The payload dir and its shard count are the fetch script's output
|
|
# layout; the fetch script must write where the env points.
|
|
grep -q '^FRANK_PRIMARY_MODEL_DIR=/home/dank/models/Qwen3.8-Flash-Next-Uncensored-FP8$' "$ENV_FILE"
|
|
grep -q '^FRANK_PRIMARY_MODEL_SHARDS=131$' "$ENV_FILE"
|
|
grep -q 'Qwen3.8-Flash-Next-Uncensored-FP8' "$DOWNLOAD"
|
|
grep -q 'orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8' "$DOWNLOAD"
|
|
}
|
|
|
|
@test "no bare HIP-reserved env var is defined" {
|
|
# HIP reads bare TEMP for its JIT cache path (2026-08-13: TEMP=1.0
|
|
# segfaulted every load), and HOST/GPU_MAX_HEAP_SIZE are the same
|
|
# class. Every key here is FRANK_PRIMARY_-prefixed.
|
|
! grep -qE '^(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$ENV_FILE"
|
|
! grep -qE '^(export )?(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$SERVE"
|
|
}
|
|
|
|
@test "the deployer gates the image digest and payload, then health-checks" {
|
|
# The deployer refuses when the pinned image is absent from rootless
|
|
# storage or the payload is missing/wrong-sharded — then clears stale
|
|
# containers (including the legacy identities), waits out the port,
|
|
# relinks/enables/restarts the root unit and health-gates it.
|
|
grep -q 'LLM_PRIMARY_CONTAINER=frank-primary-qwen' "$REMOTE_DEPLOY"
|
|
grep -q 'FRANK_PRIMARY_IMAGE' "$REMOTE_DEPLOY"
|
|
grep -q "podman images --format '{{.RepoDigests}}'" "$REMOTE_DEPLOY"
|
|
grep -q 'FRANK_PRIMARY_MODEL_SHARDS' "$REMOTE_DEPLOY"
|
|
grep -q 'config.json' "$REMOTE_DEPLOY"
|
|
grep -q 'qwen-fp8' "$REMOTE_DEPLOY"
|
|
grep -q 'glm-probe' "$REMOTE_DEPLOY"
|
|
grep -q 'wait_port_free 7770' "$REMOTE_DEPLOY"
|
|
grep -q 'relink_unit frank-primary' "$REMOTE_DEPLOY"
|
|
grep -q 'systemctl enable frank-primary.service' "$REMOTE_DEPLOY"
|
|
grep -q 'systemctl restart frank-primary.service' "$REMOTE_DEPLOY"
|
|
grep -q 'wait_for_health frank-primary http://127.0.0.1:7770/health 1800' "$REMOTE_DEPLOY"
|
|
}
|
|
|
|
@test "the deployer will not report green on a stray port-holder" {
|
|
# The 2026-09-26 false green: a leftover probe held :7770 and satisfied
|
|
# the health curl while the real unit was stopped. The deploy is only
|
|
# green when the unit's own MainPID is live behind the health answer.
|
|
grep -q 'systemctl show -p MainPID --value frank-primary.service' "$REMOTE_DEPLOY"
|
|
grep -q 'stray process holds the port' "$REMOTE_DEPLOY"
|
|
}
|