add asset/manifest.yml describing fleet hosts and neuron flavours

Adds a single source of truth for which hosts run cortex vs neuron
and which CUDA compute-capability flavour each neuron host needs:

  cortex   : hanzalova.internal
  neurons  :
    beast      → helexa-neuron-blackwell  (2x RTX 5090, sm_120)
    benjy      → helexa-neuron-ada        (RTX 4090,    sm_89)
    quadbrat   → helexa-neuron-ampere     (RTX 3060,    sm_86)

script/deploy.sh (gitignored, local-only) is updated locally to read
hosts and flavours from this manifest and dnf install the correct
helexa-neuron-<flavour> package per host. Using
'dnf install --refresh --allowerasing' lets it swap out the previous
bare helexa-neuron RPM or a different flavour without manual
intervention; the spec Conflicts: clauses keep at most one flavour
resident.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.gitea/workflows/build-prerelease.yml

@@ -94,6 +94,13 @@ jobs:
       fail-fast: false
       matrix:
         include:
+          - flavour: ampere
+            compute_cap: "86"
+            runner: cuda-13.0
+            cuda_home: /usr/local/cuda-13.0
+            build_jobs: 8
+            nvcc_threads: 4
+            cargo_features: "cuda cudnn flash-attn"
           - flavour: ada
             compute_cap: "89"
             runner: cuda-13.0
@@ -193,6 +200,7 @@ jobs:
       fail-fast: false
       matrix:
         include:
+          - flavour: ampere
           - flavour: ada
           - flavour: blackwell
     steps:

.gitea/workflows/ci.yml

@@ -16,6 +16,13 @@ env:
   SCCACHE_S3_USE_SSL: "false"
   AWS_ACCESS_KEY_ID: ${{ secrets.SCCACHE_S3_ACCESS_KEY }}
   AWS_SECRET_ACCESS_KEY: ${{ secrets.SCCACHE_S3_SECRET_KEY }}
+  # fmt, clippy, and test all run in parallel on the same `rust` runner
+  # and would otherwise share /root/.cache/act/<hash>/hostexecutor/target/,
+  # racing each other's cargo temp files (.tmpXXXXXX) and failing builds
+  # mid-compile. Give each job its own target directory so the invocations
+  # don't collide. sccache still backs the actual rustc cache, so the
+  # rebuild penalty is small.
+  CARGO_TARGET_DIR: target-${{ github.job }}
 
 jobs:
   fmt:

asset/manifest.yml

@@ -0,0 +1,30 @@
+# Helexa fleet manifest.
+#
+# Drives rolling deploys via script/deploy.sh and serves as the source
+# of truth for which hosts run cortex vs neuron, and which CUDA
+# compute-capability flavour each neuron host needs.
+#
+# Flavour ↔ NVIDIA generation ↔ compute cap:
+#   ampere    sm_86   (RTX 30 series — e.g. 3060)
+#   ada       sm_89   (RTX 40 series — e.g. 4090)
+#   blackwell sm_120  (RTX 50 series — e.g. 5090)
+#
+# The flavour determines which RPM is installed on a given neuron host:
+# helexa-neuron-<flavour>. Only one flavour may be installed at a time
+# (the packages Conflict: with each other).
+
+cortex:
+  host: hanzalova.internal
+
+neurons:
+  - host: beast.hanzalova.internal
+    flavour: blackwell
+    gpu: "2x RTX 5090"
+
+  - host: benjy.hanzalova.internal
+    flavour: ada
+    gpu: "RTX 4090"
+
+  - host: quadbrat.hanzalova.internal
+    flavour: ampere
+    gpu: "RTX 3060"