ci: add RPM packaging for cortex and neuron

- cortex.spec: gateway binary, cortex.service systemd unit, cortex.toml + models.toml config files - neuron.spec: neuron binary, neuron.service systemd unit, neuron.toml config file - Parallel CI: srpm-cortex and srpm-neuron jobs build SRPMs concurrently, then publish to separate COPR repos (helexa/cortex and helexa/neuron) - Shared cortex user/group across both packages - Example configs: cortex.example.toml, neuron.example.toml, models.example.toml Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 16:09:04 +03:00
parent 6c238f4557
commit c85d50066e
8 changed files with 266 additions and 38 deletions
--- a/.gitea/workflows/ci.yml
+++ b/.gitea/workflows/ci.yml
@@ -26,8 +26,8 @@ jobs:
      - name: Test
        run: cargo test --workspace

-  rpm:
-    name: Build SRPM
+  srpm-cortex:
+    name: Build cortex SRPM
    runs-on: fedora
    needs: check
    if: startsWith(github.ref, 'refs/tags/v')
@@ -39,14 +39,12 @@ jobs:
        run: |
          VERSION="${GITHUB_REF#refs/tags/v}"
          echo "VERSION=${VERSION}" >> "$GITHUB_OUTPUT"
-          echo "Building version: ${VERSION}"

-      - name: Stamp version into spec
+      - 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
-          echo "Stamped version ${VERSION}"

      - name: Generate source tarball
        run: |
@@ -77,19 +75,71 @@ jobs:
      - name: Upload SRPM artifact
        uses: actions/upload-artifact@v3
        with:
-          name: srpm
+          name: srpm-cortex
          path: '*.src.rpm'

-  copr:
-    name: Publish to COPR
+  srpm-neuron:
+    name: Build neuron SRPM
    runs-on: fedora
-    needs: rpm
+    needs: check
+    if: startsWith(github.ref, 'refs/tags/v')
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Determine version
+        id: version
+        run: |
+          VERSION="${GITHUB_REF#refs/tags/v}"
+          echo "VERSION=${VERSION}" >> "$GITHUB_OUTPUT"
+
+      - name: Stamp version
+        run: |
+          VERSION="${{ steps.version.outputs.VERSION }}"
+          sed -i '/\[workspace\.package\]/,/\[/{ s/^version = ".*"/version = "'"${VERSION}"'"/ }' Cargo.toml
+          sed -i "s/^Version:.*/Version:        ${VERSION}/" neuron.spec
+
+      - name: Generate source tarball
+        run: |
+          set -ex
+          VERSION="${{ steps.version.outputs.VERSION }}"
+          tar czf /tmp/neuron-${VERSION}.tar.gz \
+            --transform "s,^\.,neuron-${VERSION}," \
+            --exclude='./target' \
+            --exclude='./.git' \
+            --exclude='*.tar.gz' \
+            --exclude='*.src.rpm' \
+            .
+          mv /tmp/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/
+          rm -rf vendor/
+
+      - name: Build SRPM
+        run: |
+          rpmbuild -bs neuron.spec \
+            --define "_sourcedir $(pwd)" \
+            --define "_srcrpmdir $(pwd)"
+
+      - name: Upload SRPM artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: srpm-neuron
+          path: '*.src.rpm'
+
+  copr-cortex:
+    name: Publish cortex to COPR
+    runs-on: fedora
+    needs: srpm-cortex
    if: startsWith(github.ref, 'refs/tags/v')
    steps:
      - name: Download SRPM
        uses: actions/download-artifact@v3
        with:
-          name: srpm
+          name: srpm-cortex

      - name: Configure copr-cli
        run: |
@@ -97,4 +147,23 @@ jobs:
          echo "${{ secrets.COPR_CONFIG }}" > ~/.config/copr

      - name: Submit build to COPR
-        run: copr-cli build cortex *.src.rpm
+        run: copr-cli build helexa/cortex *.src.rpm
+
+  copr-neuron:
+    name: Publish neuron to COPR
+    runs-on: fedora
+    needs: srpm-neuron
+    if: startsWith(github.ref, 'refs/tags/v')
+    steps:
+      - name: Download SRPM
+        uses: actions/download-artifact@v3
+        with:
+          name: srpm-neuron
+
+      - name: Configure copr-cli
+        run: |
+          mkdir -p ~/.config
+          echo "${{ secrets.COPR_CONFIG }}" > ~/.config/copr
+
+      - name: Submit build to COPR
+        run: copr-cli build helexa/neuron *.src.rpm
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -590,30 +590,22 @@ Topology-aware placement (min_devices, min_device_vram_mb) deferred —
 the router currently routes based on polled model status. Catalogue
 placement matching can be added incrementally.

-### Phase 10: neuron packaging (RPM)
+### Phase 10: RPM packaging ✅

-**Goal:** `neuron` and `cortex` are installable via `dnf` from the
-grenade COPR repo.
+Completed. Both packages have RPM specs, systemd units, and example configs.
+CI builds parallel SRPMs on tag push and publishes to separate COPR repos.

-**Steps:**
-1. `neuron.spec` — RPM spec file for the neuron binary. Install to
-   `/usr/libexec/cortex/neuron`. Systemd unit
-   `neuron.service`. Config at `/etc/cortex/neuron.toml`.
-2. Update `cortex.spec` — ensure the cortex binary, config, and
-   `models.toml` are packaged correctly.
-3. Gitea Actions CI job: on tag push, build SRPM, submit to COPR.
-4. Document the install path:
-   ```sh
-   dnf copr enable grenade/cortex
-   # on the gateway host:
-   dnf install cortex
-   # on each GPU node:
-   dnf install neuron
-   ```
+- `cortex.spec` → `helexa/cortex` COPR: binary, systemd unit, config files
+- `neuron.spec` → `helexa/neuron` COPR: binary, systemd unit, config
+- `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

-**Done when:** `dnf install neuron` on a Fedora 43 host drops the
-binary, config, and systemd unit. `systemctl start neuron` runs
-discovery and serves `/discovery`.
+Install:
+```sh
+dnf copr enable helexa/cortex && dnf install cortex    # gateway host
+dnf copr enable helexa/neuron && dnf install neuron    # GPU nodes
+```

 ### Phase 11: llama.cpp harness stub

--- a/cortex.spec
+++ b/cortex.spec
@@ -1,7 +1,7 @@
 Name:           cortex
 Version:        0.1.0
 Release:        1%{?dist}
-Summary:        Inference gateway for multi-node mistral.rs clusters
+Summary:        Inference gateway for multi-node GPU clusters

 License:        GPL-3.0-or-later
 URL:            https://git.lair.cafe/helexa/cortex
@@ -15,11 +15,13 @@ BuildRequires:  cargo
 BuildRequires:  gcc
 BuildRequires:  systemd-rpm-macros

+Requires(pre):  shadow-utils
+
 %description
-Cortex is a Rust reverse-proxy that sits in front of multiple mistral.rs
-inference nodes and presents a unified OpenAI and Anthropic compatible
-API surface. It handles model routing, lifecycle management, request
-translation, and metrics collection.
+Cortex is a Rust reverse-proxy that sits in front of multiple inference
+nodes (via neuron daemons) and presents a unified OpenAI and Anthropic
+compatible API surface. It handles model routing, lifecycle management,
+request translation, and metrics collection.

 %prep
 %autosetup
@@ -38,12 +40,33 @@ cargo build --release -p cortex-cli

 %install
 install -Dm755 target/release/cortex %{buildroot}%{_bindir}/cortex
+install -Dm644 data/cortex.service %{buildroot}%{_unitdir}/cortex.service
+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
+
+%pre
+getent group cortex >/dev/null || groupadd -r cortex
+getent passwd cortex >/dev/null || useradd -r -g cortex -d /var/lib/cortex -s /sbin/nologin cortex
+
+%post
+%systemd_post cortex.service
+
+%preun
+%systemd_preun cortex.service
+
+%postun
+%systemd_postun_with_restart cortex.service

 %files
 %license LICENSE
 %doc README.md
 %{_bindir}/cortex
+%{_unitdir}/cortex.service
+%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

 %changelog
-* Mon Apr 14 2026 Rob Thijssen <grenade@rob.tn> - 0.1.0-1
+* Tue Apr 15 2026 Rob Thijssen <grenade@rob.tn> - 0.1.0-1
 - Initial package
--- a/data/cortex.service
+++ b/data/cortex.service
@@ -0,0 +1,15 @@
+[Unit]
+Description=Cortex — inference gateway for multi-node GPU clusters
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+ExecStart=/usr/bin/cortex serve --config /etc/cortex/cortex.toml
+Restart=on-failure
+RestartSec=5
+User=cortex
+Group=cortex
+
+[Install]
+WantedBy=multi-user.target
--- a/data/neuron.service
+++ b/data/neuron.service
@@ -0,0 +1,15 @@
+[Unit]
+Description=Neuron — per-node GPU discovery and harness daemon for cortex
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+ExecStart=/usr/bin/neuron --config /etc/cortex/neuron.toml
+Restart=on-failure
+RestartSec=5
+User=cortex
+Group=cortex
+
+[Install]
+WantedBy=multi-user.target
--- a/models.example.toml
+++ b/models.example.toml
@@ -0,0 +1,29 @@
+# models.example.toml — model catalogue
+#
+# Copy to /etc/cortex/models.toml and adjust for your environment.
+# Describes how to serve each model. Cortex matches these profiles
+# against discovered neuron topologies for placement decisions.
+
+[[models]]
+id = "your-org/large-model"
+harness = "mistralrs"
+quant = "Q4_K_M"
+vram_mb = 19000
+min_devices = 2
+min_device_vram_mb = 10000
+pinned_on = ["gpu-large"]
+
+[[models]]
+id = "your-org/medium-model"
+harness = "mistralrs"
+quant = "Q6_K"
+vram_mb = 12000
+min_devices = 1
+pinned_on = ["gpu-medium"]
+
+[[models]]
+id = "your-org/embedding-model"
+harness = "mistralrs"
+quant = "Q8_0"
+vram_mb = 8000
+min_devices = 1
--- a/neuron.example.toml
+++ b/neuron.example.toml
@@ -0,0 +1,16 @@
+# neuron.example.toml — example configuration
+#
+# Copy to /etc/cortex/neuron.toml and adjust for your environment.
+#
+# Environment variable overrides use NEURON_ prefix with __ separators:
+#   NEURON_PORT=9090
+
+port = 9090
+
+# -- Harnesses ---------------------------------------------------------------
+# Each [[harnesses]] entry declares an inference engine managed by neuron.
+
+[[harnesses]]
+name = "mistralrs"
+endpoint = "http://localhost:8080"
+systemd_unit = "mistralrs.service"
--- a/neuron.spec
+++ b/neuron.spec
@@ -0,0 +1,69 @@
+Name:           neuron
+Version:        0.1.0
+Release:        1%{?dist}
+Summary:        Per-node GPU discovery and harness management daemon for cortex
+
+License:        GPL-3.0-or-later
+URL:            https://git.lair.cafe/helexa/cortex
+Source0:        %{name}-%{version}.tar.gz
+Source1:        %{name}-%{version}-vendor.tar.gz
+
+ExclusiveArch:  x86_64
+
+BuildRequires:  rust >= 1.85
+BuildRequires:  cargo
+BuildRequires:  gcc
+BuildRequires:  systemd-rpm-macros
+
+Requires(pre):  shadow-utils
+
+%description
+Neuron is a per-node daemon for cortex inference clusters. It discovers
+local GPU hardware via nvidia-smi, manages inference harnesses (mistral.rs,
+llama.cpp), and exposes an HTTP API for model lifecycle management.
+
+%prep
+%autosetup
+tar xf %{SOURCE1}
+mkdir -p .cargo
+cat > .cargo/config.toml << 'EOF'
+[source.crates-io]
+replace-with = "vendored-sources"
+
+[source.vendored-sources]
+directory = "vendor"
+EOF
+
+%build
+cargo build --release -p neuron
+
+%install
+install -Dm755 target/release/neuron %{buildroot}%{_bindir}/neuron
+install -Dm644 data/neuron.service %{buildroot}%{_unitdir}/neuron.service
+install -dm750 %{buildroot}%{_sysconfdir}/cortex
+install -Dm640 neuron.example.toml %{buildroot}%{_sysconfdir}/cortex/neuron.toml
+
+%pre
+getent group cortex >/dev/null || groupadd -r cortex
+getent passwd cortex >/dev/null || useradd -r -g cortex -d /var/lib/cortex -s /sbin/nologin cortex
+
+%post
+%systemd_post neuron.service
+
+%preun
+%systemd_preun neuron.service
+
+%postun
+%systemd_postun_with_restart neuron.service
+
+%files
+%license LICENSE
+%doc README.md
+%{_bindir}/neuron
+%{_unitdir}/neuron.service
+%dir %attr(750,root,cortex) %{_sysconfdir}/cortex
+%config(noreplace) %attr(640,root,cortex) %{_sysconfdir}/cortex/neuron.toml
+
+%changelog
+* Tue Apr 15 2026 Rob Thijssen <grenade@rob.tn> - 0.1.0-1
+- Initial package