frank-large: CIRU v4.4.1 Orca cutover — root unit, one stream, full context
Operator call 2026-09-19: switch the iGPU endpoint from halogen-flash-server to jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca on the CIRU v4.4.1 runtime with the QSA window hotfix (host build against the private ROCm 10 SDK), one stream of the full 262144 trained window. The service leaves the quadlet shape for a root unit (the same shape as frank-small and frank-medium: a private-SDK host binary has no image to install and no generated unit to dodge); the halogen quadlet is archived, the deploy handler retires it on the host, gates on 7770, and its stray-run sweep matches the model path so it cannot take frank-small down.
This commit is contained in:
Frank committed
1 parent
d374ab963f
commit
b6ce3afb1f
9 files changed
+317
-406
No files matched your search
+101
-93
@@ -1,113 +1,121 @@
|
||||
#!/usr/bin/env bats
|
||||
# Seam: the frank-large halogen-flash-server quadlet on dankclaw.
|
||||
# halogen-flash-server replaced ik_llama.cpp again on 2026-09-16, so this
|
||||
# service is once more a rootless Quadlet container on the gfx1151 iGPU. This
|
||||
# seam pins what a flag list cannot show: the boot-persistent podman posture
|
||||
# (both device nodes, memlock, the create-time image contract), the
|
||||
# matched ctx/pool/slots set that IS the two-conversation promise, the
|
||||
# co-tenancy budget the arena and reserve are chosen for, the image handoff to
|
||||
# frank-small, and a deploy handler that retires the previous ROOT unit without
|
||||
# deleting it.
|
||||
# Seam: the frank-large CIRU v4.4.1 root unit on dankclaw.
|
||||
#
|
||||
# The 2026-09-19 cutover moved this service out of the halogen-flash-server
|
||||
# quadlet and onto the CIRU v4.4.1 runtime (QSA window hotfix) serving
|
||||
# jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca, as a ROOT unit on a host build -- the
|
||||
# same shape as frank-small and frank-medium, because a private-SDK host
|
||||
# binary has no container image to install and no generated unit to dodge.
|
||||
# This seam pins what a flag list cannot show: the operator's one-stream /
|
||||
# full-context shape, the payload the launcher refuses to start without, a
|
||||
# deploy handler that retires the halogen quadlet without deleting it and
|
||||
# gates on the port, and the fact that the sweep for a stray benchmark run
|
||||
# cannot take frank-small down with it.
|
||||
|
||||
load helpers
|
||||
|
||||
QUADLET="$REPO_ROOT/dankclaw/frank-large/quadlet/frank-large.container"
|
||||
ENV_FILE="$REPO_ROOT/scripts/frank-large.env"
|
||||
UNIT="$REPO_ROOT/scripts/frank-large.service"
|
||||
SERVE="$REPO_ROOT/scripts/serve-frank-large.sh"
|
||||
FETCH="$REPO_ROOT/scripts/download-frank-large-orca.sh"
|
||||
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
|
||||
|
||||
@test "the frank-large quadlet exists where the deployer installs it from" {
|
||||
[ -f "$QUADLET" ]
|
||||
@test "the frank-large unit, env and serve files exist where the deployer installs them from" {
|
||||
[ -f "$ENV_FILE" ]
|
||||
[ -f "$UNIT" ]
|
||||
[ -x "$SERVE" ]
|
||||
}
|
||||
|
||||
@test "frank-large is boot-persistent, self-healing and container-shaped" {
|
||||
grep -q '^WantedBy=default.target$' "$QUADLET"
|
||||
grep -q '^Restart=on-failure$' "$QUADLET"
|
||||
grep -q '^RestartSec=' "$QUADLET"
|
||||
grep -q '^Pull=never$' "$QUADLET"
|
||||
# The localhost/-aliased tag is what create-time resolution needs on this
|
||||
# host; the deployer pulls the ghcr.io ref and re-tags it.
|
||||
grep -q '^Image=localhost/peonist-ai/halogen-flash-server:' "$QUADLET"
|
||||
@test "frank-large is boot-persistent, self-healing and unprivileged" {
|
||||
grep -q '^WantedBy=multi-user.target$' "$UNIT"
|
||||
grep -q '^Restart=on-failure$' "$UNIT"
|
||||
grep -q '^RestartSec=' "$UNIT"
|
||||
grep -q '^User=dank$' "$UNIT"
|
||||
# The engine pins staging buffers and the PLE pager's hot window; the
|
||||
# memlock budget must be unbounded or the load fails on the RLIMIT.
|
||||
grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
|
||||
# The unit runs the repo's own serve script with the repo's env.
|
||||
grep -q 'ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh' "$UNIT"
|
||||
grep -q 'FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-large.env' "$UNIT"
|
||||
}
|
||||
|
||||
@test "frank-large has the gfx1151 devices and the image's documented posture" {
|
||||
grep -q '^AddDevice=/dev/kfd$' "$QUADLET"
|
||||
grep -q '^AddDevice=/dev/dri$' "$QUADLET"
|
||||
grep -q '^PodmanArgs=--ipc=host --security-opt seccomp=unconfined$' "$QUADLET"
|
||||
grep -q '^Ulimit=memlock=-1:-1$' "$QUADLET"
|
||||
# The weights mount must stay read-write: the first start downloads into it.
|
||||
grep -q '^Volume=/home/dank/models/halogen:/models$' "$QUADLET"
|
||||
@test "the operator's shape is one stream of the full trained window" {
|
||||
local ctx slots
|
||||
ctx="$(sed -nE 's/^CONTEXT_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||||
slots="$(sed -nE 's/^PARALLEL_SLOTS=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||||
# 262144 is the model's trained window and the GGUF carries no rope
|
||||
# scaling; the operator asked for full context.
|
||||
[ "$ctx" -eq 262144 ]
|
||||
# One slot. This is also the drafter's constraint: the launcher refuses
|
||||
# MTP with more than one slot, so the two cannot drift apart silently.
|
||||
[ "$slots" -eq 1 ]
|
||||
grep -q '^ENABLE_MTP=1$' "$ENV_FILE"
|
||||
}
|
||||
|
||||
@test "frank-large keeps the fleet alias and publishes only the API port" {
|
||||
grep -q '^Environment=HALOGEN_MODEL_ID=frank-large$' "$QUADLET"
|
||||
grep -q '^PublishPort=7770:8731$' "$QUADLET"
|
||||
# The engine's own listener stays inside the container: it is unauthenticated.
|
||||
! grep -q 'PublishPort=.*8730' "$QUADLET"
|
||||
}
|
||||
|
||||
@test "the KV pool is exactly two conversations of the per-request ceiling" {
|
||||
local ctx pool slots
|
||||
ctx="$(sed -nE 's/^Environment=HALOGEN_CTX=([0-9]+)$/\1/p' "$QUADLET")"
|
||||
pool="$(sed -nE 's/^Environment=HALOGEN_KV_POOL_POSITIONS=([0-9]+)$/\1/p' "$QUADLET")"
|
||||
slots="$(sed -nE 's/^Environment=HALOGEN_KV_SLOTS=([0-9]+)$/\1/p' "$QUADLET")"
|
||||
[ -n "$ctx" ] && [ -n "$pool" ] && [ -n "$slots" ]
|
||||
# The deployed promise is two resident conversations: the pool is twice the
|
||||
# ceiling, one slot per conversation. Slots still oversubscribe the pool for
|
||||
# any real request, because admission reserves prompt + max_tokens.
|
||||
[ "$pool" -eq $((ctx * 2)) ]
|
||||
[ "$slots" -eq 2 ]
|
||||
}
|
||||
|
||||
@test "the prefill arena stays inside the range the vendor tested" {
|
||||
local max_tok reserve
|
||||
max_tok="$(sed -nE 's/^Environment=HALOGEN_MAX_TOK=([0-9]+)$/\1/p' "$QUADLET")"
|
||||
reserve="$(sed -nE 's/^Environment=HALOGEN_HOST_RESERVE_GIB=([0-9]+)$/\1/p' "$QUADLET")"
|
||||
[ -n "$max_tok" ] && [ -n "$reserve" ]
|
||||
# 32768 is the vendor default; 65536 cannot boot on this host because the
|
||||
# arena alone outgrows the device budget. The arena is a per-call prefill
|
||||
# chunk, so a smaller value costs prefill speed, not context.
|
||||
[ "$max_tok" -le 32768 ]
|
||||
[ "$max_tok" -ge 16384 ]
|
||||
[ "$reserve" -ge 15 ]
|
||||
}
|
||||
|
||||
@test "frank-large loads no vision tower: the fleet's image path is frank-small" {
|
||||
! grep -q 'HALOGEN_VISION_TOWER' "$QUADLET"
|
||||
@test "frank-large stays text-only until the projector is enabled" {
|
||||
grep -q '^ENABLE_VISION=0$' "$ENV_FILE"
|
||||
# The fleet's image path is frank-small; the projector is on disk and is
|
||||
# one env flip away, but models.yml declares frank-large text-only.
|
||||
grep -q -- '--mmproj' "$REPO_ROOT/scripts/serve-frank-small.sh"
|
||||
}
|
||||
|
||||
@test "the deploy handler retires the previous ROOT unit without deleting it" {
|
||||
grep -q 'retire_root_llm_large' "$REMOTE_DEPLOY"
|
||||
grep -q 'systemctl stop frank-large.service' "$REMOTE_DEPLOY"
|
||||
grep -q 'systemctl disable frank-large.service' "$REMOTE_DEPLOY"
|
||||
@test "the serve script pins the hotfix runtime and refuses a missing build" {
|
||||
grep -q 'ciru-runtime-v4.4.1-qsa-hotfix' "$SERVE"
|
||||
grep -q 'build-gfx1151-sdk/bin/llama-server' "$SERVE"
|
||||
grep -q 'run-orca-server.sh' "$SERVE"
|
||||
# A missing runtime or payload is a deploy error with a pointer, not a
|
||||
# restart loop.
|
||||
grep -q 'missing built runtime' "$SERVE"
|
||||
grep -q 'missing target model' "$SERVE"
|
||||
# The Qwen3.8 template keeps prior thinking blocks across turns only
|
||||
# when the kwarg is set; the launcher passes --jinja but no kwargs.
|
||||
grep -q 'preserve_thinking' "$SERVE"
|
||||
}
|
||||
|
||||
@test "the payload is fetched resumably and verified by sha256" {
|
||||
grep -q 'jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca' "$FETCH"
|
||||
grep -q -- '-fL -C -' "$FETCH"
|
||||
grep -q 'parts.json' "$FETCH"
|
||||
grep -q 'sha256sum -c SHA256SUMS' "$FETCH"
|
||||
# The PLE sidecar is the largest transport part; the script must fetch
|
||||
# and verify it, not just the GGUF.
|
||||
grep -q 'ple.payload.bin' "$FETCH"
|
||||
}
|
||||
|
||||
@test "the fleet endpoint and alias survive the cutover" {
|
||||
grep -q '^HOST=0.0.0.0$' "$ENV_FILE"
|
||||
grep -q '^PORT=7770$' "$ENV_FILE"
|
||||
grep -q '^MODEL_DIR=/home/dank/models/Qwen3.8-Flash-CIRU-STRIX-Orca$' "$ENV_FILE"
|
||||
}
|
||||
|
||||
@test "the deploy handler retires the halogen quadlet without deleting it" {
|
||||
grep -q 'retire_halogen_large_quadlet' "$REMOTE_DEPLOY"
|
||||
grep -q 'HOME/.AGENTTRASH' "$REMOTE_DEPLOY"
|
||||
! grep -qE '(^|[^[:alnum:]_])rm (-[a-zA-Z]+ )?.*frank-large' "$REMOTE_DEPLOY"
|
||||
}
|
||||
|
||||
@test "the deploy handler installs the quadlet and gates the first start on weights" {
|
||||
grep -q 'install_quadlet frank-large dankclaw/frank-large/quadlet frank-large' "$REMOTE_DEPLOY"
|
||||
grep -q 'wait_for_llm_large_ready' "$REMOTE_DEPLOY"
|
||||
grep -q 'qwen38-flash-next-w4b.hgn' "$REMOTE_DEPLOY"
|
||||
grep -q '127.0.0.1:7770/health' "$REMOTE_DEPLOY"
|
||||
}
|
||||
|
||||
@test "the ik_llama.cpp runtime that held this service is archived, not live" {
|
||||
# Its files must not sit in scripts/ where a stale root unit could still be
|
||||
# pointed at them, and must not be gone either: .AGENTTRASH is the rollback.
|
||||
local retired
|
||||
for retired in frank-large.env.ik-llama.cpp frank-large.service.ik-llama.cpp \
|
||||
serve-frank-large.sh.ik-llama.cpp; do
|
||||
[ -f "$REPO_ROOT/scripts/.AGENTTRASH/$retired" ]
|
||||
done
|
||||
[ ! -e "$REPO_ROOT/scripts/frank-large.env" ]
|
||||
[ ! -e "$REPO_ROOT/scripts/frank-large.service" ]
|
||||
[ ! -e "$REPO_ROOT/scripts/serve-frank-large.sh" ]
|
||||
}
|
||||
|
||||
@test "the deploy handler waits for the predecessor to release the port" {
|
||||
# The 2026-09-16 cutover failed at exactly this: the ik server's socket was
|
||||
# still on 7770 when pasta tried to bind it ("Address already in use"), and
|
||||
# the container died on it. Restart=on-failure recovered minutes later, but
|
||||
# a deploy that starts a doomed container has not deployed anything.
|
||||
@test "the deploy handler installs the root unit, gates the port and refuses a missing payload" {
|
||||
grep -q 'relink_unit frank-large' "$REMOTE_DEPLOY"
|
||||
grep -q 'systemctl enable frank-large.service' "$REMOTE_DEPLOY"
|
||||
grep -q 'wait_port_free 7770' "$REMOTE_DEPLOY"
|
||||
grep -q '^wait_port_free() {' "$REMOTE_DEPLOY"
|
||||
}
|
||||
grep -q '127.0.0.1:7770/health' "$REMOTE_DEPLOY"
|
||||
grep -q 'LLM_LARGE_MODEL' "$REMOTE_DEPLOY"
|
||||
grep -q 'LLM_LARGE_PLE' "$REMOTE_DEPLOY"
|
||||
}
|
||||
|
||||
@test "the stray-run sweep cannot take frank-small down" {
|
||||
# frank-small on this host is ALSO a llama-server. The sweep must match
|
||||
# the model path, not the binary name, or a frank-large deploy restarts
|
||||
# the 3090 endpoint.
|
||||
grep -q "pkill -f 'Qwen3.8-Flash-CIRU-STRIX-Orca'" "$REMOTE_DEPLOY"
|
||||
# ...and only inside the large handler: extract it and check there is no
|
||||
# bare binary-name pkill in it.
|
||||
local large
|
||||
large="$(sed -n '/^deploy_llm_large() {/,/^}/p' "$REMOTE_DEPLOY")"
|
||||
! grep -q 'pkill -x llama-server' <<<"$large"
|
||||
}
|
||||
|
||||
@test "the halogen quadlet is archived, not live" {
|
||||
[ ! -e "$REPO_ROOT/dankclaw/frank-large/quadlet/frank-large.container" ]
|
||||
[ -f "$REPO_ROOT/dankclaw/.AGENTTRASH/frank-large.container.halogen" ]
|
||||
}
|
||||
Reference in new issue
Block a user