Compare commits
19 Commits
v0.1.9
...
7f797b0265
| Author | SHA1 | Date | |
|---|---|---|---|
|
7f797b0265
|
|||
|
5a0360c1d5
|
|||
|
472c0e8737
|
|||
|
|
b9d8e30058 | ||
|
25f75fe552
|
|||
|
3f94c50817
|
|||
|
3e1fb60076
|
|||
|
|
9bf987888c | ||
|
abe4ff7ccc
|
|||
|
7c3390a4e1
|
|||
|
2ff062da0e
|
|||
|
|
357f858a29 | ||
|
556e5293dc
|
|||
|
1d90238b01
|
|||
|
d99b25fb8a
|
|||
|
034da319f1
|
|||
|
|
7ece281617 | ||
|
3bb5b3c425
|
|||
|
|
9fa51ad874 |
@@ -18,54 +18,38 @@ env:
|
||||
AWS_SECRET_ACCESS_KEY: ${{ secrets.SCCACHE_S3_SECRET_KEY }}
|
||||
|
||||
jobs:
|
||||
check:
|
||||
name: Format, lint, build, test
|
||||
runs-on: fedora
|
||||
fmt:
|
||||
name: Format
|
||||
runs-on: rust
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- run: cargo fmt --check --all
|
||||
|
||||
- name: Cache cargo registry and target
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/bin
|
||||
~/.cargo/registry/index
|
||||
~/.cargo/registry/cache
|
||||
~/.cargo/git/db
|
||||
target
|
||||
key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
|
||||
restore-keys: |
|
||||
${{ runner.os }}-cargo-
|
||||
clippy:
|
||||
name: Clippy
|
||||
runs-on: rust
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- run: cargo clippy --workspace -- -D warnings
|
||||
- run: sccache --show-stats
|
||||
|
||||
- name: Ensure sccache with S3 support
|
||||
env:
|
||||
RUSTC_WRAPPER: ""
|
||||
run: |
|
||||
if sccache --version 2>/dev/null && sccache --show-stats 2>/dev/null; then
|
||||
echo "sccache with S3 support already installed"
|
||||
else
|
||||
cargo install sccache --features s3 --locked
|
||||
fi
|
||||
|
||||
- name: Check formatting
|
||||
run: cargo fmt --check --all
|
||||
|
||||
- name: Clippy
|
||||
run: cargo clippy --workspace -- -D warnings
|
||||
|
||||
- name: Test
|
||||
run: cargo test --workspace
|
||||
|
||||
- name: Show sccache stats
|
||||
run: sccache --show-stats
|
||||
test:
|
||||
name: Test
|
||||
runs-on: rust
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- run: cargo test --workspace
|
||||
- run: sccache --show-stats
|
||||
|
||||
srpm-cortex:
|
||||
name: Build cortex SRPM
|
||||
runs-on: fedora
|
||||
needs: check
|
||||
runs-on: rpm
|
||||
needs: [fmt, clippy, test]
|
||||
if: startsWith(github.ref, 'refs/tags/v')
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Determine version
|
||||
id: version
|
||||
@@ -79,6 +63,12 @@ jobs:
|
||||
sed -i '/\[workspace\.package\]/,/\[/{ s/^version = ".*"/version = "'"${VERSION}"'"/ }' Cargo.toml
|
||||
sed -i "s/^Version:.*/Version: ${VERSION}/" cortex.spec
|
||||
|
||||
- name: Generate changelog entry
|
||||
uses: https://git.lair.cafe/actions/rpm-changelog@v1
|
||||
with:
|
||||
spec: cortex.spec
|
||||
version: ${{ steps.version.outputs.VERSION }}
|
||||
|
||||
- name: Generate source tarball
|
||||
run: |
|
||||
set -ex
|
||||
@@ -113,11 +103,13 @@ jobs:
|
||||
|
||||
srpm-neuron:
|
||||
name: Build neuron SRPM
|
||||
runs-on: fedora
|
||||
needs: check
|
||||
runs-on: rpm
|
||||
needs: [fmt, clippy, test]
|
||||
if: startsWith(github.ref, 'refs/tags/v')
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Determine version
|
||||
id: version
|
||||
@@ -129,31 +121,37 @@ jobs:
|
||||
run: |
|
||||
VERSION="${{ steps.version.outputs.VERSION }}"
|
||||
sed -i '/\[workspace\.package\]/,/\[/{ s/^version = ".*"/version = "'"${VERSION}"'"/ }' Cargo.toml
|
||||
sed -i "s/^Version:.*/Version: ${VERSION}/" neuron.spec
|
||||
sed -i "s/^Version:.*/Version: ${VERSION}/" helexa-neuron.spec
|
||||
|
||||
- name: Generate changelog entry
|
||||
uses: https://git.lair.cafe/actions/rpm-changelog@v1
|
||||
with:
|
||||
spec: helexa-neuron.spec
|
||||
version: ${{ steps.version.outputs.VERSION }}
|
||||
|
||||
- name: Generate source tarball
|
||||
run: |
|
||||
set -ex
|
||||
VERSION="${{ steps.version.outputs.VERSION }}"
|
||||
tar czf /tmp/neuron-${VERSION}.tar.gz \
|
||||
--transform "s,^\.,neuron-${VERSION}," \
|
||||
tar czf /tmp/helexa-neuron-${VERSION}.tar.gz \
|
||||
--transform "s,^\.,helexa-neuron-${VERSION}," \
|
||||
--exclude='./target' \
|
||||
--exclude='./.git' \
|
||||
--exclude='*.tar.gz' \
|
||||
--exclude='*.src.rpm' \
|
||||
.
|
||||
mv /tmp/neuron-${VERSION}.tar.gz .
|
||||
mv /tmp/helexa-neuron-${VERSION}.tar.gz .
|
||||
|
||||
- name: Vendor Rust dependencies
|
||||
run: |
|
||||
VERSION="${{ steps.version.outputs.VERSION }}"
|
||||
cargo vendor vendor/
|
||||
tar czf neuron-${VERSION}-vendor.tar.gz vendor/
|
||||
tar czf helexa-neuron-${VERSION}-vendor.tar.gz vendor/
|
||||
rm -rf vendor/
|
||||
|
||||
- name: Build SRPM
|
||||
run: |
|
||||
rpmbuild -bs neuron.spec \
|
||||
rpmbuild -bs helexa-neuron.spec \
|
||||
--define "_sourcedir $(pwd)" \
|
||||
--define "_srcrpmdir $(pwd)"
|
||||
|
||||
@@ -165,7 +163,7 @@ jobs:
|
||||
|
||||
copr-cortex:
|
||||
name: Publish cortex to COPR
|
||||
runs-on: fedora
|
||||
runs-on: fedora-43
|
||||
needs: srpm-cortex
|
||||
steps:
|
||||
- name: Download SRPM
|
||||
@@ -176,13 +174,13 @@ jobs:
|
||||
- name: Publish to COPR
|
||||
uses: https://git.lair.cafe/actions/copr-publish@v1
|
||||
with:
|
||||
project: helexa/cortex
|
||||
project: helexa/helexa
|
||||
srpm: "*.src.rpm"
|
||||
copr-config: ${{ secrets.COPR_CONFIG }}
|
||||
|
||||
copr-neuron:
|
||||
name: Publish neuron to COPR
|
||||
runs-on: fedora
|
||||
runs-on: fedora-43
|
||||
needs: srpm-neuron
|
||||
steps:
|
||||
- name: Download SRPM
|
||||
@@ -193,31 +191,53 @@ jobs:
|
||||
- name: Publish to COPR
|
||||
uses: https://git.lair.cafe/actions/copr-publish@v1
|
||||
with:
|
||||
project: helexa/neuron
|
||||
project: helexa/helexa
|
||||
srpm: "*.src.rpm"
|
||||
copr-config: ${{ secrets.COPR_CONFIG }}
|
||||
|
||||
bump-version:
|
||||
name: Bump version in source
|
||||
runs-on: fedora
|
||||
runs-on: rust
|
||||
needs: [copr-cortex, copr-neuron]
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Stamp version and push
|
||||
- name: Determine version
|
||||
id: version
|
||||
run: echo "VERSION=${GITHUB_REF#refs/tags/v}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Stamp version
|
||||
run: |
|
||||
VERSION="${{ steps.version.outputs.VERSION }}"
|
||||
sed -i '/\[workspace\.package\]/,/\[/{ s/^version = ".*"/version = "'"${VERSION}"'"/ }' Cargo.toml
|
||||
sed -i "s/^Version:.*/Version: ${VERSION}/" cortex.spec
|
||||
sed -i "s/^Version:.*/Version: ${VERSION}/" helexa-neuron.spec
|
||||
cargo check --workspace 2>/dev/null || true
|
||||
|
||||
- name: Generate cortex changelog entry
|
||||
uses: https://git.lair.cafe/actions/rpm-changelog@v1
|
||||
with:
|
||||
spec: cortex.spec
|
||||
version: ${{ steps.version.outputs.VERSION }}
|
||||
|
||||
- name: Generate helexa-neuron changelog entry
|
||||
uses: https://git.lair.cafe/actions/rpm-changelog@v1
|
||||
with:
|
||||
spec: helexa-neuron.spec
|
||||
version: ${{ steps.version.outputs.VERSION }}
|
||||
|
||||
- name: Commit and push
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
run: |
|
||||
VERSION="${GITHUB_REF#refs/tags/v}"
|
||||
sed -i '/\[workspace\.package\]/,/\[/{ s/^version = ".*"/version = "'"${VERSION}"'"/ }' Cargo.toml
|
||||
sed -i "s/^Version:.*/Version: ${VERSION}/" cortex.spec
|
||||
sed -i "s/^Version:.*/Version: ${VERSION}/" neuron.spec
|
||||
cargo check --workspace 2>/dev/null || true
|
||||
VERSION="${{ steps.version.outputs.VERSION }}"
|
||||
git config user.name "Gitea Actions"
|
||||
git config user.email "actions@git.lair.cafe"
|
||||
git add Cargo.toml Cargo.lock cortex.spec neuron.spec
|
||||
git add Cargo.toml Cargo.lock cortex.spec helexa-neuron.spec
|
||||
if git diff --cached --quiet; then
|
||||
echo "Version already at ${VERSION}"
|
||||
echo "Nothing to commit for ${VERSION}"
|
||||
else
|
||||
git commit -m "chore: bump version to ${VERSION}"
|
||||
git remote set-url origin "https://gitea-actions:${GITEA_TOKEN}@git.lair.cafe/helexa/cortex.git"
|
||||
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@@ -5,3 +5,4 @@
|
||||
.vscode/
|
||||
cortex.toml
|
||||
doc/plan/*
|
||||
script/deploy.sh
|
||||
|
||||
35
CLAUDE.md
35
CLAUDE.md
@@ -125,7 +125,8 @@ automatically. Clippy warnings must be resolved, not suppressed with
|
||||
- One or more GPU nodes running mistral.rs on port 8080
|
||||
- Optionally a metrics-only node (no GPU) for Prometheus/Grafana
|
||||
- Each node runs `mistralrs serve` on port 8080
|
||||
- Gateway listens on port 8000 (API) and 9100 (metrics)
|
||||
- Gateway listens on port 31313 (API) and 31314 (metrics)
|
||||
- neuron listens on port 13131 on each GPU host
|
||||
- TLS terminated at gateway or via nginx; internal traffic is plaintext over WireGuard
|
||||
|
||||
## Conventions
|
||||
@@ -380,7 +381,7 @@ processes (one process per loaded model, each on its own port).
|
||||
|
||||
## neuron API
|
||||
|
||||
neuron exposes an HTTP API on port 9090 that cortex polls and calls.
|
||||
neuron exposes an HTTP API on port 13131 that cortex polls and calls.
|
||||
|
||||
```
|
||||
GET /discovery
|
||||
@@ -424,8 +425,8 @@ endpoint. cortex.toml shrinks to:
|
||||
|
||||
```toml
|
||||
[gateway]
|
||||
listen = "0.0.0.0:8000"
|
||||
metrics_listen = "0.0.0.0:9100"
|
||||
listen = "0.0.0.0:31313"
|
||||
metrics_listen = "0.0.0.0:31314"
|
||||
|
||||
[eviction]
|
||||
strategy = "lru"
|
||||
@@ -433,15 +434,15 @@ defrag_after_cycles = 50
|
||||
|
||||
[[neurons]]
|
||||
name = "beast"
|
||||
endpoint = "http://beast.hanzalova.internal:9090"
|
||||
endpoint = "http://beast.hanzalova.internal:13131"
|
||||
|
||||
[[neurons]]
|
||||
name = "benjy"
|
||||
endpoint = "http://benjy.kosherinata.internal:9090"
|
||||
endpoint = "http://benjy.hanzalova.internal:13131"
|
||||
|
||||
[[neurons]]
|
||||
name = "quadbrat"
|
||||
endpoint = "http://quadbrat.hanzalova.internal:9090"
|
||||
endpoint = "http://quadbrat.hanzalova.internal:13131"
|
||||
```
|
||||
|
||||
On startup and periodically, cortex calls `GET /discovery` and
|
||||
@@ -521,7 +522,7 @@ cortex/
|
||||
│ │ └── metrics.rs # prometheus exporter (unchanged)
|
||||
│ ├── neuron/ # node plane (replaces cortex-agent)
|
||||
│ │ └── src/
|
||||
│ │ ├── main.rs # binary entrypoint, axum server on :9090
|
||||
│ │ ├── main.rs # binary entrypoint, axum server on :13131
|
||||
│ │ ├── discovery.rs # nvidia-smi, device enumeration
|
||||
│ │ ├── health.rs # runtime GPU polling
|
||||
│ │ ├── api.rs # HTTP handlers for /discovery, /models, etc.
|
||||
@@ -595,16 +596,24 @@ placement matching can be added incrementally.
|
||||
Completed. Both packages have RPM specs, systemd units, and example configs.
|
||||
CI builds parallel SRPMs on tag push and publishes to separate COPR repos.
|
||||
|
||||
- `cortex.spec` → `helexa/cortex` COPR: binary, systemd unit, config files
|
||||
- `neuron.spec` → `helexa/neuron` COPR: binary, systemd unit, config
|
||||
- `cortex.spec` — installs the `cortex` binary. Package name keeps the
|
||||
short `cortex` because no Fedora package collides with it.
|
||||
- `helexa-neuron.spec` — installs the `neuron` binary under package name
|
||||
`helexa-neuron`. Renamed from bare `neuron` to avoid collision with
|
||||
Fedora's NEURON neural-simulation package
|
||||
(https://src.fedoraproject.org/rpms/neuron); binary, systemd unit,
|
||||
system user, and config dir all stay named `neuron` since those are
|
||||
project-local contexts.
|
||||
- `data/cortex.service`, `data/neuron.service` — systemd units
|
||||
- `cortex.example.toml`, `neuron.example.toml`, `models.example.toml`
|
||||
- CI: parallel `srpm-cortex` + `srpm-neuron` jobs, then parallel COPR publish
|
||||
- CI: parallel `srpm-cortex` + `srpm-neuron` jobs, then parallel COPR
|
||||
publish to a single project `helexa/helexa` hosting both packages.
|
||||
|
||||
Install:
|
||||
```sh
|
||||
dnf copr enable helexa/cortex && dnf install cortex # gateway host
|
||||
dnf copr enable helexa/neuron && dnf install neuron # GPU nodes
|
||||
dnf copr enable helexa/helexa
|
||||
dnf install cortex # gateway host
|
||||
dnf install helexa-neuron # GPU nodes
|
||||
```
|
||||
|
||||
### Phase 11: llama.cpp harness stub
|
||||
|
||||
8
Cargo.lock
generated
8
Cargo.lock
generated
@@ -351,7 +351,7 @@ checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
|
||||
|
||||
[[package]]
|
||||
name = "cortex-cli"
|
||||
version = "0.1.7"
|
||||
version = "0.1.16"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"clap",
|
||||
@@ -366,7 +366,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cortex-core"
|
||||
version = "0.1.7"
|
||||
version = "0.1.16"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"async-trait",
|
||||
@@ -381,7 +381,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cortex-gateway"
|
||||
version = "0.1.7"
|
||||
version = "0.1.16"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"axum",
|
||||
@@ -1184,7 +1184,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "neuron"
|
||||
version = "0.1.7"
|
||||
version = "0.1.16"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"async-trait",
|
||||
|
||||
@@ -8,7 +8,7 @@ members = [
|
||||
]
|
||||
|
||||
[workspace.package]
|
||||
version = "0.1.7"
|
||||
version = "0.1.16"
|
||||
edition = "2024"
|
||||
license = "GPL-3.0-or-later"
|
||||
repository = "https://git.lair.cafe/helexa/cortex"
|
||||
|
||||
@@ -88,8 +88,8 @@ WantedBy=multi-user.target
|
||||
```toml
|
||||
# cortex.toml
|
||||
[gateway]
|
||||
listen = "0.0.0.0:8000"
|
||||
metrics_listen = "0.0.0.0:9100"
|
||||
listen = "0.0.0.0:31313"
|
||||
metrics_listen = "0.0.0.0:31314"
|
||||
|
||||
[eviction]
|
||||
strategy = "lru" # lru | priority
|
||||
@@ -143,7 +143,7 @@ cortex serve --config cortex.toml
|
||||
cortex status
|
||||
|
||||
# list all models across nodes
|
||||
curl http://localhost:8000/v1/models
|
||||
curl http://localhost:31313/v1/models
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
@@ -3,11 +3,11 @@
|
||||
# Copy to cortex.toml and adjust for your environment.
|
||||
#
|
||||
# Environment variable overrides use CORTEX_ prefix with __ separators:
|
||||
# CORTEX_GATEWAY__LISTEN=0.0.0.0:9000
|
||||
# CORTEX_GATEWAY__LISTEN=0.0.0.0:31313
|
||||
|
||||
[gateway]
|
||||
listen = "0.0.0.0:8000"
|
||||
metrics_listen = "0.0.0.0:9100"
|
||||
listen = "0.0.0.0:31313"
|
||||
metrics_listen = "0.0.0.0:31314"
|
||||
|
||||
[eviction]
|
||||
strategy = "lru"
|
||||
|
||||
40
cortex.spec
40
cortex.spec
@@ -1,5 +1,5 @@
|
||||
Name: cortex
|
||||
Version: 0.1.7
|
||||
Version: 0.1.16
|
||||
Release: 1%{?dist}
|
||||
Summary: Inference gateway for multi-node GPU clusters
|
||||
|
||||
@@ -21,12 +21,16 @@ BuildRequires: systemd-rpm-macros
|
||||
|
||||
Requires(pre): shadow-utils
|
||||
Requires: systemd
|
||||
Requires: firewalld-filesystem
|
||||
|
||||
# rpm's sysusers provides-generator only emits versioned user(cortex) when
|
||||
# the u-line has GECOS/home/shell fields. %attr(,,cortex) in %files emits
|
||||
# an unversioned Requires: user(cortex), so we provide it explicitly.
|
||||
# systemd-rpm-macros ships a unit dep generator that parses User=/Group=
|
||||
# from our .service file and emits Requires: user(cortex)/group(cortex).
|
||||
# rpm's sysusers provides-generator emits the unversioned form for groups
|
||||
# but only a versioned user(cortex) = <base64> for users with GECOS/home/
|
||||
# shell. Provide the unversioned user(cortex) explicitly so dnf can resolve
|
||||
# the auto-generated Requires. Without this, dnf5 silently filters the
|
||||
# package and reports "Nothing to do".
|
||||
Provides: user(cortex)
|
||||
Provides: group(cortex)
|
||||
|
||||
%description
|
||||
Cortex is a Rust reverse-proxy that sits in front of multiple inference
|
||||
@@ -53,9 +57,10 @@ cargo build --release -p cortex-cli
|
||||
install -Dm755 target/release/cortex %{buildroot}%{_bindir}/cortex
|
||||
install -Dm644 data/cortex.service %{buildroot}%{_unitdir}/cortex.service
|
||||
install -Dm644 data/cortex-sysusers.conf %{buildroot}%{_sysusersdir}/cortex.conf
|
||||
install -dm750 %{buildroot}%{_sysconfdir}/cortex
|
||||
install -Dm640 cortex.example.toml %{buildroot}%{_sysconfdir}/cortex/cortex.toml
|
||||
install -Dm640 models.example.toml %{buildroot}%{_sysconfdir}/cortex/models.toml
|
||||
install -Dm644 data/cortex-firewalld.xml %{buildroot}%{_prefix}/lib/firewalld/services/cortex.xml
|
||||
install -dm755 %{buildroot}%{_sysconfdir}/cortex
|
||||
install -Dm644 cortex.example.toml %{buildroot}%{_sysconfdir}/cortex/cortex.toml
|
||||
install -Dm644 models.example.toml %{buildroot}%{_sysconfdir}/cortex/models.toml
|
||||
|
||||
%pre
|
||||
%sysusers_create_compat %{_builddir}/%{name}-%{version}/data/cortex-sysusers.conf
|
||||
@@ -75,10 +80,21 @@ install -Dm640 models.example.toml %{buildroot}%{_sysconfdir}/cortex/models.toml
|
||||
%{_bindir}/cortex
|
||||
%{_unitdir}/cortex.service
|
||||
%{_sysusersdir}/cortex.conf
|
||||
%dir %attr(750,root,cortex) %{_sysconfdir}/cortex
|
||||
%config(noreplace) %attr(640,root,cortex) %{_sysconfdir}/cortex/cortex.toml
|
||||
%config(noreplace) %attr(640,root,cortex) %{_sysconfdir}/cortex/models.toml
|
||||
%{_prefix}/lib/firewalld/services/cortex.xml
|
||||
%dir %{_sysconfdir}/cortex
|
||||
%config(noreplace) %{_sysconfdir}/cortex/cortex.toml
|
||||
%config(noreplace) %{_sysconfdir}/cortex/models.toml
|
||||
|
||||
%changelog
|
||||
* Tue Apr 15 2026 Rob Thijssen <grenade@rob.tn> - 0.1.0-1
|
||||
* Thu Apr 16 2026 Gitea Actions <actions@git.lair.cafe> - 0.1.16-1
|
||||
- chore: ignore local deploy script
|
||||
- chore: move default ports out of common-collision ranges
|
||||
- ci: drop actions/cache for cargo registry and target
|
||||
|
||||
* Thu Apr 16 2026 Gitea Actions <actions@git.lair.cafe> - 0.1.14-1
|
||||
- ci: publish both packages to a single helexa/helexa COPR project
|
||||
- fix(rpm): rename neuron package to helexa-neuron
|
||||
- ci: commit generated %changelog entries back to main
|
||||
|
||||
* Wed Apr 15 2026 Rob Thijssen <grenade@rob.tn> - 0.1.0-1
|
||||
- Initial package
|
||||
|
||||
@@ -23,7 +23,7 @@ enum Commands {
|
||||
/// Print the fleet status (models, nodes, health).
|
||||
Status {
|
||||
/// Gateway API endpoint to query.
|
||||
#[arg(short, long, default_value = "http://localhost:8000")]
|
||||
#[arg(short, long, default_value = "http://localhost:31313")]
|
||||
endpoint: String,
|
||||
},
|
||||
}
|
||||
|
||||
@@ -22,9 +22,9 @@ fn default_models_path() -> String {
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct GatewaySettings {
|
||||
/// Address to listen on for API requests (e.g. "0.0.0.0:8000")
|
||||
/// Address to listen on for API requests (e.g. "0.0.0.0:31313")
|
||||
pub listen: String,
|
||||
/// Address to listen on for Prometheus metrics (e.g. "0.0.0.0:9100")
|
||||
/// Address to listen on for Prometheus metrics (e.g. "0.0.0.0:31314")
|
||||
pub metrics_listen: String,
|
||||
}
|
||||
|
||||
@@ -50,7 +50,7 @@ pub enum EvictionStrategy {
|
||||
pub struct NeuronEndpoint {
|
||||
/// Human-readable node name (e.g. "beast")
|
||||
pub name: String,
|
||||
/// Base URL of the neuron daemon (e.g. "http://beast.internal:9090")
|
||||
/// Base URL of the neuron daemon (e.g. "http://beast.internal:13131")
|
||||
pub endpoint: String,
|
||||
}
|
||||
|
||||
@@ -70,8 +70,8 @@ impl Default for GatewayConfig {
|
||||
fn default() -> Self {
|
||||
Self {
|
||||
gateway: GatewaySettings {
|
||||
listen: "0.0.0.0:8000".into(),
|
||||
metrics_listen: "0.0.0.0:9100".into(),
|
||||
listen: "0.0.0.0:31313".into(),
|
||||
metrics_listen: "0.0.0.0:31314".into(),
|
||||
},
|
||||
eviction: EvictionSettings {
|
||||
strategy: EvictionStrategy::Lru,
|
||||
|
||||
@@ -6,7 +6,7 @@ use std::collections::HashMap;
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct NodeState {
|
||||
pub name: String,
|
||||
/// Base URL of the neuron daemon (e.g. "http://beast.internal:9090").
|
||||
/// Base URL of the neuron daemon (e.g. "http://beast.internal:13131").
|
||||
pub endpoint: String,
|
||||
pub healthy: bool,
|
||||
pub models: HashMap<String, ModelEntry>,
|
||||
|
||||
@@ -17,7 +17,7 @@ pub struct NeuronConfig {
|
||||
}
|
||||
|
||||
fn default_port() -> u16 {
|
||||
9090
|
||||
13131
|
||||
}
|
||||
|
||||
impl NeuronConfig {
|
||||
@@ -33,7 +33,7 @@ impl NeuronConfig {
|
||||
impl Default for NeuronConfig {
|
||||
fn default() -> Self {
|
||||
Self {
|
||||
port: 9090,
|
||||
port: 13131,
|
||||
harnesses: vec![],
|
||||
}
|
||||
}
|
||||
|
||||
7
data/cortex-firewalld.xml
Normal file
7
data/cortex-firewalld.xml
Normal file
@@ -0,0 +1,7 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<service>
|
||||
<short>cortex</short>
|
||||
<description>Cortex — inference gateway for multi-node GPU clusters</description>
|
||||
<port protocol="tcp" port="31313"/>
|
||||
<port protocol="tcp" port="31314"/>
|
||||
</service>
|
||||
6
data/neuron-firewalld.xml
Normal file
6
data/neuron-firewalld.xml
Normal file
@@ -0,0 +1,6 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<service>
|
||||
<short>helexa-neuron</short>
|
||||
<description>Neuron — per-node GPU discovery and harness daemon for cortex</description>
|
||||
<port protocol="tcp" port="13131"/>
|
||||
</service>
|
||||
@@ -1,7 +1,10 @@
|
||||
Name: neuron
|
||||
Version: 0.1.7
|
||||
Name: helexa-neuron
|
||||
Version: 0.1.16
|
||||
Release: 1%{?dist}
|
||||
Summary: Per-node GPU discovery and harness management daemon for cortex
|
||||
# Package name disambiguates from Fedora's existing "neuron" package
|
||||
# (NEURON neural simulation environment from Yale). Binary, systemd
|
||||
# unit, and system user are still called "neuron" for brevity.
|
||||
|
||||
License: GPL-3.0-or-later
|
||||
URL: https://git.lair.cafe/helexa/cortex
|
||||
@@ -21,12 +24,16 @@ BuildRequires: systemd-rpm-macros
|
||||
|
||||
Requires(pre): shadow-utils
|
||||
Requires: systemd
|
||||
Requires: firewalld-filesystem
|
||||
|
||||
# rpm's sysusers provides-generator only emits versioned user(neuron) when
|
||||
# the u-line has GECOS/home/shell fields. %attr(,,neuron) in %files emits
|
||||
# an unversioned Requires: user(neuron), so we provide it explicitly.
|
||||
# systemd-rpm-macros ships a unit dep generator that parses User=/Group=
|
||||
# from our .service file and emits Requires: user(neuron)/group(neuron).
|
||||
# rpm's sysusers provides-generator emits the unversioned form for groups
|
||||
# but only a versioned user(neuron) = <base64> for users with GECOS/home/
|
||||
# shell. Provide the unversioned user(neuron) explicitly so dnf can resolve
|
||||
# the auto-generated Requires. Without this, dnf5 silently filters the
|
||||
# package and reports "Nothing to do".
|
||||
Provides: user(neuron)
|
||||
Provides: group(neuron)
|
||||
|
||||
%description
|
||||
Neuron is a per-node daemon for cortex inference clusters. It discovers
|
||||
@@ -52,8 +59,9 @@ cargo build --release -p neuron
|
||||
install -Dm755 target/release/neuron %{buildroot}%{_bindir}/neuron
|
||||
install -Dm644 data/neuron.service %{buildroot}%{_unitdir}/neuron.service
|
||||
install -Dm644 data/neuron-sysusers.conf %{buildroot}%{_sysusersdir}/neuron.conf
|
||||
install -dm750 %{buildroot}%{_sysconfdir}/neuron
|
||||
install -Dm640 neuron.example.toml %{buildroot}%{_sysconfdir}/neuron/neuron.toml
|
||||
install -Dm644 data/neuron-firewalld.xml %{buildroot}%{_prefix}/lib/firewalld/services/helexa-neuron.xml
|
||||
install -dm755 %{buildroot}%{_sysconfdir}/neuron
|
||||
install -Dm644 neuron.example.toml %{buildroot}%{_sysconfdir}/neuron/neuron.toml
|
||||
|
||||
%pre
|
||||
%sysusers_create_compat %{_builddir}/%{name}-%{version}/data/neuron-sysusers.conf
|
||||
@@ -73,9 +81,20 @@ install -Dm640 neuron.example.toml %{buildroot}%{_sysconfdir}/neuron/neuron.toml
|
||||
%{_bindir}/neuron
|
||||
%{_unitdir}/neuron.service
|
||||
%{_sysusersdir}/neuron.conf
|
||||
%dir %attr(750,root,neuron) %{_sysconfdir}/neuron
|
||||
%config(noreplace) %attr(640,root,neuron) %{_sysconfdir}/neuron/neuron.toml
|
||||
%{_prefix}/lib/firewalld/services/helexa-neuron.xml
|
||||
%dir %{_sysconfdir}/neuron
|
||||
%config(noreplace) %{_sysconfdir}/neuron/neuron.toml
|
||||
|
||||
%changelog
|
||||
* Tue Apr 15 2026 Rob Thijssen <grenade@rob.tn> - 0.1.0-1
|
||||
* Thu Apr 16 2026 Gitea Actions <actions@git.lair.cafe> - 0.1.16-1
|
||||
- chore: ignore local deploy script
|
||||
- chore: move default ports out of common-collision ranges
|
||||
- ci: drop actions/cache for cargo registry and target
|
||||
|
||||
* Thu Apr 16 2026 Gitea Actions <actions@git.lair.cafe> - 0.1.14-1
|
||||
- ci: publish both packages to a single helexa/helexa COPR project
|
||||
- fix(rpm): rename neuron package to helexa-neuron
|
||||
- ci: commit generated %changelog entries back to main
|
||||
|
||||
* Wed Apr 15 2026 Rob Thijssen <grenade@rob.tn> - 0.1.0-1
|
||||
- Initial package
|
||||
@@ -3,9 +3,9 @@
|
||||
# Copy to /etc/neuron/neuron.toml and adjust for your environment.
|
||||
#
|
||||
# Environment variable overrides use NEURON_ prefix with __ separators:
|
||||
# NEURON_PORT=9090
|
||||
# NEURON_PORT=13131
|
||||
|
||||
port = 9090
|
||||
port = 13131
|
||||
|
||||
# -- Harnesses ---------------------------------------------------------------
|
||||
# Each [[harnesses]] entry declares an inference engine managed by neuron.
|
||||
|
||||
Reference in New Issue
Block a user