* feat(images): add a vllm-serving AMI as a stacked mkosi profile
LaunchServingVM resolves its AMI by the tags spinifex:managed-by=bedrock and
spinifex:bedrock-role=vllm-serving. No image carried either, so every Ensure
failed at resolveServingAMI. The only GPU image ships the NVIDIA driver and
Docker but no Python, no vLLM and no serving unit, so tagging it would have
moved the failure from admission to first boot.
Add a vllm profile that stacks onto gpu-nvidia and owns the whole guest side
of the launcher contract: the runtime, vllm-serve.service, the weights mount
and the tags. vLLM is baked into a uv-managed venv rather than pulled as a
container at boot — a runtime docker pull of vllm/vllm-openai is known to
stall this platform's write plane, and mkosi's unprivileged build has no
daemon to bake an image from anyway.
Also bring images/mkosi.profiles/ under make test-images. Its scripts have no
.sh suffix, so the existing name glob skipped exactly the files worth linting;
sources are found by shebang instead.
* fix(images): make the vllm postinst survive the build sandbox
Two failures found by actually running the build.
uv installs to /usr/local/bin, which mkosi's postinst PATH need not carry, so
`command -v uv` reported a good install as missing. Call it by absolute path,
and check it the same way.
`vllm --version` initialises device config and dies with "Failed to infer
device type" on a builder with no GPU, so it could never have verified
anything. Assert the pinned version through package metadata instead, which
also catches a version mismatch rather than merely a broken entrypoint.
* fix(images): pin the serving AMI datasource and mirror cloud-init to the console
A serving VM boots through LaunchSystemInstance, so it comes up dual-NIC with a
fw_cfg netcfg blob and takes its user-data solely from IMDS — the same shape as
the EKS control plane. That path carries a cloud-init datasource pin; the vllm
profile never got one, and the base config deliberately leaves datasource_list
unpinned, so the serving image was the only system VM booting without it.
Reuse the EKS pin rather than copying it. The 99- prefix is load-bearing:
read_conf_d() applies cloud.cfg.d in REVERSE and mergemanydict() is
first-source-wins, so a 90- name loses to cloud-init's own 90_dpkg.cfg ('_'
sorts above '-') and the pin is discarded in silence. The postinst asserts the
MERGED datasource_list via cloud-init's own read_conf_with_confd rather than
checking the file exists, because it existed at 90- too and did nothing there.
Also mirror every cloud-init stage to the serial console. A serving VM is
headless, and a guest that wedges before handover never surrenders
/var/log/cloud-init-output.log, so the console get-console-output reads is the
only channel an operator has.
The images_test.go case covers the two tags resolveServingAMI filters on; it
matches on those alone and never on name, so a typo hides the image entirely.
* fix(images): make the dhcpcd data-NIC lease genuinely one-shot
dhcp_oneshot() promised to configure the link and exit "leaving no daemon
to fight cloud-init", but the dhcpcd branch passed only -q, which is quiet
rather than one-shot. Every Ubuntu image takes that branch, so a dhcpcd
daemon survived on the data NIC holding the control socket.
cloud-init's Ec2 datasource then runs its own ephemeral dhcpcd on the same
NIC. Instead of spawning, dhcpcd forwards the invocation to the resident
daemon as a control command and exits 0, and --dumplease returns the
resident daemon's lease, so discovery looks successful. Cleanup then waits
for a pid file at /run/dhcpcd/<iface>-4.pid that no process ever wrote,
spinning its full 30000 x 10ms budget: init-local stalls for exactly 300s
on every system-instance boot.
Adding -1 exits once the interface is configured and -p keeps the address
and routes across that exit. Both are needed; -1 alone tears the link back
down. The test now models the real clients — the stub stays resident unless
given the flag that makes its client exit, and the dhcpcd branch is forced
by dropping udhcpc from PATH rather than left to whether the host happens
to have /usr/share/udhcpc/default.script.
* fix(images): serve without a CUDA toolkit and stop vllm-serve crash-looping
vLLM picks FlashInfer for top-k/top-p sampling, and FlashInfer JIT-compiles
that kernel on first use. The serving image ships the driver and the
container toolkit but no nvcc, so the sampler warmup died with "Could not
find nvcc and default cuda_home='/usr/local/cuda' doesn't exist" minutes
into a GPU cold start, after the model had already loaded.
VLLM_USE_FLASHINFER_SAMPLER=0 selects vLLM's native top-k/top-p sampler,
which is the same operation with no CUDA toolchain at runtime. Everything
else on the serving path is already precompiled in the wheels: the attention
backend resolves to FLASH_ATTN and CUDA graph capture completes, both
without nvcc. Baking FlashInfer's AOT modules is the alternative if the
fused kernel is ever wanted, and it keeps the toolchain in the builder
rather than the appliance.
The unit had Restart=on-failure with no bound, so an unfixable start failure
restarted forever and buried its own first traceback under identical copies
on the serial console — the only view an operator has of a headless guest.
StartLimitIntervalSec/StartLimitBurst make it report instead.
The postinst asserts the installed unit carries the sampler setting, for the
same reason the datasource pin is asserted there: the alternative is finding
out at runtime, on a GPU, five minutes in.
Also corrects the shared datasource pin's header, which still claimed it
installs as 90-spinifex-ec2-imds.cfg. It is installed at 99- by the vllm
profile precisely because a 90- name loses the reverse-sorted, first-source-
wins cloud.cfg.d merge to cloud-init's own 90_dpkg.cfg.
* fix(bedrock): raise the serving-endpoint readiness bound to 15 minutes
The 5 minute bound was chosen before any cold start had been measured, and
its own comment asked to be corrected once a model actually ran on wattle.
It now has: Llama 3.2 1B on an RTX A1000 reached "Application startup
complete" 257.6s after launch, leaving ~42s of margin on the smallest model
this platform can serve, with a cold torch.compile accounting for 26.3s of
it. A bigger card and a bigger model are unmeasured.
The two failure modes are not symmetric. Too low tears down an endpoint that
was about to come up and reports it as a failed launch; too high only makes
a genuinely stuck launch take longer to give up. So the bound is set well
clear of the single data point rather than close to it.
The CLI's own wait moves to 20 minutes to stay above it. The daemon starts
its clock when the VM is launched, up to a minute after the CLI starts its
own, so leaving both at 15 would expire the client first and report a bare
"timed out" in place of the daemon's abort, which carries the reason.
* fix: give the Ochre daemon a routed port in the Bedrock system VPC
The readiness probe and every InvokeModel call dial a serving VM's
system-VPC address from inside the daemon, but that subnet lives in OVN
on br-int and the host has no route to it, so a healthy VM never reached
READY.
Each daemon now owns an ENI in the system VPC's private subnet, bound to
an OVS internal port on br-int by iface-id, exactly as ovn-controller
binds a guest tap. The ENI address is installed at the subnet's prefix
length, which is what supplies the connected route. BaseURL is unchanged:
the address it already carried is now reachable.
Describe-or-create keyed on a per-node description, since ENIs carry no
tag filter, so a restart or a second endpoint reuses one address instead
of leaking one per launch. The port is ensured before anything else the
launch creates: a VM the daemon cannot dial holds a GPU for the whole
readiness window before unwinding.
Both actions carried no scope, so their policy check evaluated against "*".
Matching is pattern-to-value, so a statement whose Resource is a specific ARN
never matches "*" — a Deny fencing an instance blocked the scoped
ModifyDBInstance and DeleteDBInstance but not a snapshot of the same instance.
The principal could snapshot the fenced instance, restore it under a name the
Deny does not cover, set a master password of their choosing and read the data.
Each is scoped to its source: the instance for a create, the snapshot for a
restore, which breaks the chain at its first step. Both identifiers are required
on their action and ResourceARN already falls back to "*" when absent, so this
narrows where the identifier is present and is a no-op where it is not.
Evaluating both ARNs per action, for AWS parity, is deliberately left out: it
turns the scope into a slice across all 13 scoped entries and touches the shared
dispatcher call site.
* feat: add spx admin ochre endpoint ensure/describe/list/delete
The daemon subscribes all four bedrock.endpoint.* subjects, but nothing in
production calls their NATS client, so the serving-endpoint lifecycle could
not be exercised at all in a running system. This gives an operator a direct
way to drive it.
ensure --wait polls describe until READY and reports the elapsed time, since
the daemon replies STARTING as soon as it claims the model and the launch
outlives the request. That is the measured cold start.
Also corrects the weights stage tokenizer rule in COMMANDS.md, which still
described both tokenizer files as required rather than either.
* test: cover the ochre endpoint Run wrappers' connect and exit paths
* fix: treat an empty endpoint bucket as no endpoints, not an error
ListEndpoints was the only kvutil.Keys caller not handling ErrNoKeysFound,
so 'ochre endpoint list' failed on a cluster that had never launched one.
weights stage created the snapshot at the viperblock layer only, writing
the block checkpoint and config.json but not the metadata.json that
CreateVolume resolves a SnapshotId through. The endpoint launcher clones
the weights volume via ec2.CreateVolume, so every launch failed with
InvalidSnapshot.NotFound against a snapshot that was present on disk.
The GPU model table was only ever used to report VRAM, so wrong or missing
entries were cosmetic. Bedrock's capacity check is the first code that rejects
on VRAM, which turns every latent data error into an admission decision.
Correct seven entries verified against pci.ids — most seriously 1002:7448,
labelled Instinct MI300X at 192GB when it is a Radeon Pro W7900 at 48GB, a
4x over-report that admits a model which then OOMs at weight load. Record the
smallest capacity where one PCI ID spans several cards, since under-reporting
refuses an endpoint an operator can see and override while over-reporting
fails later and looks like a vLLM bug.
Widen the table so common datacenter, workstation and consumer cards resolve
without an operator-supplied override, and apply GPUModelOverrides to the pool
devices as well as the advertised model, so the override reaches the code that
actually gates. An override with no memory_mib is left alone rather than
wiping discovered VRAM, since the config cannot distinguish it from a
deliberate zero.
MemoryMiB 0 stays the "undiscoverable" sentinel, but checkCapacity no longer
counts it as a device with no VRAM: an otherwise-free device now reports which
card is unknown and how to fix it.
* fix: make the predastore readiness gate a real readiness probe
checkPredastoreReady only did a TCP dial + close, so a listening socket
satisfied it well before predastore could serve TLS. In CI this passed
in 170 microseconds, 0.72s after predastore opened its listener, and
recovery started against a backend that wasn't serving yet — predastore
logged the probe itself as a TLS handshake EOF.
Replace the dial with an HTTPS GET against the configured predastore
endpoint on a package-level client (hoisted out of the 2s poll loop),
with a per-request 3s context timeout. Any HTTP response counts as
ready, including 403 from this deliberately unsigned request, which is
exactly what an unauthenticated S3 GET returns. Only a transport or TLS
failure means not-ready.
This narrows the race window and removes the spurious TLS-handshake-EOF
log lines predastore emits on every daemon start, but it does not close
the window on its own: predastore can serve TLS before its storage
backend answers reads correctly. The load-bearing fix is the viperblock
VBState read retry landing separately.
* style: trim the predastore readiness comments to three lines
GetPasswordData returned an empty string both when the guest had not emitted a
password yet and when it never could, because the launch key pair was ED25519
and cannot perform PKCS#1 v1.5 encryption. The two are indistinguishable, so a
caller in the second case polls forever with no signal.
An empty result on a Windows instance whose launch key is not RSA now returns
InvalidKeyPair.Type naming the cause and the fix. Every uncertainty keeps the
old empty result: a populated blob always wins, Linux is never judged, and an
unresolvable key is not treated as evidence of the wrong type.
Josh Siviour