feat[notask]: build @qvac/fabric with the ROCm/HIP backend

.github/workflows/on-pr-fabric.yml

@@ -189,6 +189,9 @@ jobs:
       sha: ${{ github.event.pull_request.base.sha || github.sha }}
       pr_head_sha: ${{ github.event.pull_request.head.sha }}
       workdir: packages/fabric
+      # fabric pulls qvac-fabric[hip-backend]; ggml-config find_dependency(hip)
+      # needs ROCm on the lint runner at configure time.
+      include-rocm-sdk: true
 
   detect-fabric-stack:
     if: needs.authorize.outputs.allowed == 'true'

.github/workflows/prebuilds-fabric.yml

@@ -44,4 +44,9 @@ jobs:
       repository: ${{ inputs.repository }}
       artifact-name-prefix: fabric-
       include-vulkan-sdk: true
+      # Cross-compile the ROCm/HIP backend (gfx1151) into the linux-x64 prebuild
+      # so every @qvac/fabric consumer gets libqvac-ggml-hip.so from the shared
+      # runtime. No AMD GPU needed on the runner; fail-safe if the ROCm install
+      # or the port feature is absent.
+      include-rocm: true
     secrets: inherit

packages/fabric/CHANGELOG.md

@@ -1,5 +1,25 @@
 # Changelog
 
+## [0.9.0] - 2026-08-25
+
+### Added
+
+- ROCm/HIP compute backend (`libqvac-ggml-hip.so`, gfx1151 / Strix Halo) in the
+  linux-x64 prebuild, via the `qvac-fabric[hip-backend]` feature. It ships as a
+  `GGML_BACKEND_DL` module under `prebuilds/linux-x64/qvac__fabric/` alongside
+  Vulkan, so every consumer of the shared runtime can select it — previously the
+  feature was requested per-consumer by `@qvac/vla-ggml`, which no longer builds
+  its own ggml. The DL loader skips the module on non-AMD hosts, and the build is
+  fail-safe: no ROCm SDK at build time means a Vulkan/CPU-only prebuild.
+
+### Changed
+
+- `prebuilds-fabric.yml` sets `include-rocm: true` so the linux-x64 prebuild
+  cross-compiles the HIP backend, and `on-pr-fabric.yml`'s `cpp-lint` sets
+  `include-rocm-sdk: true` because `ggml-config.cmake` resolves
+  `find_dependency(hip/hipblas/rocblas)` at configure time. No AMD GPU is
+  required on either runner.
+
 ## [0.8.0] - 2026-08-24
 
 ### Changed

packages/fabric/README.md

@@ -25,6 +25,8 @@ pattern. See [INTEGRATION.md](./INTEGRATION.md) for the consumer guide.
   ship under `prebuilds/<platform>/qvac__fabric/` and are loaded at runtime via
   `ggml_backend_load_all_from_path()`. On **macOS, Windows, and iOS** the backends
   are linked statically inside `qvac__fabric.bare` and self-register on load.
+  On **linux-x64** this includes the ROCm/HIP backend (`libqvac-ggml-hip.so`,
+  gfx1151) alongside Vulkan; the DL loader skips it on non-AMD hosts.
 
 ## Architecture
 
@@ -72,7 +74,7 @@ npm run build   # bare-make generate && bare-make build && bare-make install
 
 | Platform | Triplet | Backends |
 |----------|---------|----------|
-| Linux | `x64-linux`, `arm64-linux` | shared `.so` under `prebuilds/<platform>/qvac__fabric/` |
+| Linux | `x64-linux`, `arm64-linux` | shared `.so` under `prebuilds/<platform>/qvac__fabric/` (x64 also ships ROCm/HIP) |
 | macOS | `arm64-osx` | static (CPU, Metal) inside `.bare` |
 | Windows | (default MSVC) | static inside `.bare` |
 | Android | `arm64-android` | shared `.so` under `prebuilds/<platform>/qvac__fabric/` |

packages/fabric/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qvac/fabric",
-  "version": "0.8.0",
+  "version": "0.9.0",
   "description": "Shared bare addon hosting the qvac-fabric (forked llama.cpp + ggml) runtime for QVAC inference addons",
   "addon": true,
   "engines": {

packages/fabric/vcpkg.json

@@ -6,7 +6,10 @@
     },
     {
       "name": "qvac-fabric",
-      "version>=": "10297.0.0"
+      "version>=": "10297.0.0",
+      "features": [
+        "hip-backend"
+      ]
     },
     {
       "name": "qvac-lint-cpp",