CI / test (push) Successful in 1m32s
Three places where the system took the infrastructure's word for something and would have failed silently on real hardware. A declared fabric adapter that is not on the node. Fabric membership has to be configuration — OpenSM's default subnet prefix is identical on every fabric, so a matching prefix proves nothing — but taking it entirely on trust was a different mistake. A typo, or a card that enumerated differently after a reboot, produced NCCL_IB_HCA naming an adapter that does not exist. An adapter with no ACTIVE port. Physically linked with no subnet manager sits in INIT: it looks healthy to anything counting adapters, carries no data, survives a reboot, and looks like a software problem. Discovery had recorded port state all along and placement only ever asked whether a fabric had any adapters listed. Both end the same way — the replica starts, passes its health checks, and hangs on its first all-reduce, which is the failure the fabric invariant exists to prevent arriving through a door nobody was watching. The agent now compares declared against discovered, where both are visible for the only time, and does not advertise a fabric that cannot carry traffic. The reason is logged on the machine that knows it, because the operator who typed the adapter name is the only person who can fix it. The fabric's rate is the slowest active link, since a collective runs at the speed of its slowest. And NVLink topology, which no published binary could see. NVML is its only source, the bindings need cgo, and CGO_ENABLED=0 is deliberate so the portable binary runs on an older libc. The cost was silent: tensor groups fall back to the lowest free indices, which is right on an SXM board with NVSwitch and wrong on a PCIe box where bridges pair specific cards — a group straddling two of them runs several times slower and nothing says so. Releases now also publish an nvml build for those nodes, and llmgw_gpu_nvlink_peers makes the difference visible: a flat zero across a fleet means the topology is unknown rather than absent. A test that declared mlx5_0 and mlx5_1 on a node whose sysfs held neither had been passing, because nothing compared the two. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
114 lines
4.8 KiB
YAML
114 lines
4.8 KiB
YAML
# Attaches binaries to a release when a version tag is pushed.
|
|
#
|
|
# Without this a release is a git tag, and installing llmgw on a node means
|
|
# having a Go toolchain and the source. The onboarding script copies a binary
|
|
# from wherever it is run, which works and quietly makes whoever runs it the
|
|
# build server.
|
|
name: Release
|
|
|
|
on:
|
|
push:
|
|
tags: ["v*"]
|
|
workflow_dispatch:
|
|
|
|
jobs:
|
|
build:
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
with:
|
|
# Tags are what the version string is built from, and a shallow clone
|
|
# has none of them.
|
|
fetch-depth: 0
|
|
|
|
- uses: actions/setup-go@v5
|
|
with:
|
|
go-version-file: go.mod
|
|
cache: true
|
|
|
|
- name: Build
|
|
run: |
|
|
set -euo pipefail
|
|
version="${GITHUB_REF_NAME:-$(git describe --tags --always)}"
|
|
mkdir -p dist
|
|
|
|
# CGO_ENABLED=0 is the whole point: the binary has to run on a node
|
|
# whose libc is older than the builder's, and llmgw has no C
|
|
# dependency — modernc.org/sqlite is pure Go precisely so this stays
|
|
# true.
|
|
for target in linux/amd64 linux/arm64 darwin/amd64 darwin/arm64; do
|
|
os="${target%/*}"; arch="${target#*/}"
|
|
name="llmgw-${version}-${os}-${arch}"
|
|
echo "building $name"
|
|
CGO_ENABLED=0 GOOS="$os" GOARCH="$arch" go build \
|
|
-trimpath \
|
|
-ldflags "-s -w -X gitea.mynodes.xyz/ilker/llmgw/internal/version.Version=${version}" \
|
|
-o "dist/${name}" ./cmd/llmgw
|
|
(cd dist && sha256sum "${name}" >> checksums.txt)
|
|
done
|
|
|
|
# An NVML build for nodes with NVLink, which the portable binary
|
|
# cannot serve.
|
|
#
|
|
# NVML is the only source of NVLink topology, its bindings need cgo,
|
|
# and cgo is exactly what CGO_ENABLED=0 above exists to avoid. So the
|
|
# portable binary silently falls back to taking the lowest free GPU
|
|
# indices — right on an SXM box with NVSwitch, and wrong on a PCIe
|
|
# box where NVLink bridges pair specific cards: a tensor group
|
|
# straddling two bridges runs several times slower and nothing says
|
|
# so. Shipping only the portable build meant nobody could have that
|
|
# topology without building it themselves.
|
|
#
|
|
# Dynamically linked against the host's libc by necessity, so it is
|
|
# published beside the portable one rather than instead of it.
|
|
if command -v gcc >/dev/null; then
|
|
nvml_name="llmgw-${version}-linux-amd64-nvml"
|
|
CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go build \
|
|
-tags nvml -trimpath \
|
|
-ldflags "-s -w -X gitea.mynodes.xyz/ilker/llmgw/internal/version.Version=${version}" \
|
|
-o "dist/${nvml_name}" ./cmd/llmgw
|
|
(cd dist && sha256sum "${nvml_name}" >> checksums.txt)
|
|
else
|
|
echo "no C toolchain; skipping the nvml build" >&2
|
|
fi
|
|
|
|
# Proof the artifact runs at all before it is published. It cannot
|
|
# test the cross-compiled ones, which is why the native build is
|
|
# checked rather than assumed.
|
|
./dist/llmgw-${version}-linux-amd64 --version
|
|
cat dist/checksums.txt
|
|
|
|
- name: Attach to the release
|
|
env:
|
|
TOKEN: ${{ secrets.GITEA_TOKEN }}
|
|
run: |
|
|
set -euo pipefail
|
|
if [ -z "${TOKEN:-}" ]; then
|
|
echo "No GITEA_TOKEN secret, so nothing can be uploaded."
|
|
echo "Add one in the repository's Actions settings with package or"
|
|
echo "repository write scope; the binaries are in dist/ meanwhile."
|
|
exit 1
|
|
fi
|
|
tag="${GITHUB_REF_NAME}"
|
|
api="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
|
|
|
|
# The release usually exists already, created by hand with its notes.
|
|
id=$(curl -sS -H "Authorization: token $TOKEN" "$api/releases/tags/$tag" \
|
|
| sed -n 's/.*"id":\([0-9]*\).*/\1/p' | head -1)
|
|
if [ -z "$id" ]; then
|
|
echo "creating release $tag"
|
|
id=$(curl -sS -X POST -H "Authorization: token $TOKEN" \
|
|
-H "Content-Type: application/json" \
|
|
-d "{\"tag_name\":\"$tag\",\"name\":\"$tag\"}" \
|
|
"$api/releases" | sed -n 's/.*"id":\([0-9]*\).*/\1/p' | head -1)
|
|
fi
|
|
[ -n "$id" ] || { echo "could not find or create the release" >&2; exit 1; }
|
|
|
|
for f in dist/*; do
|
|
echo "uploading $(basename "$f")"
|
|
curl -sS -X POST -H "Authorization: token $TOKEN" \
|
|
-F "attachment=@$f" \
|
|
"$api/releases/$id/assets?name=$(basename "$f")" >/dev/null
|
|
done
|
|
echo "attached $(ls dist | wc -l) files to $tag"
|