perf(llama-cpp-rocm): tune for Strix Halo (gfx1151)

- Restrict rocmGpuTargets to gfx1151 (Radeon 8060S, RDNA 3.5) — smaller
  closure, faster compile, no wasted device kernels.
- Enable GGML_HIP_ROCWMMA_FATTN: rocWMMA-backed flash attention is a
  major win on RDNA3+ for the GPU-offloaded attention path.
- Enable GGML_HIP_GRAPHS to lower per-token launch overhead.
- Add rocwmma to buildInputs to satisfy the WMMA path.

llama-server on halo runs with -ngl 99 --flash-attn on, so these flags
target the hot path. CPU-side AVX-512 was skipped intentionally — Zen 5
has it, but with full GPU offload the CPU paths barely run.

overlays/unstable/default.nix

@@ -12,18 +12,33 @@ final: prev: {
     # nodejs_20
     ;
 
-  llama-cpp-rocm = channels.unstable.llama-cpp-rocm.overrideAttrs (_: {
+  # Tuned for Strix Halo (Ryzen AI Max+ 395 / Radeon 8060S, gfx1151).
-    src = prev.fetchFromGitHub {
+  llama-cpp-rocm =
-      owner = "am17an";
+    (channels.unstable.llama-cpp.override {
-      repo = "llama.cpp";
+      rocmSupport = true;
-      rev = "267f8afe857b7bd1a49e4fde9138ab0f7be36625";
+      rocmGpuTargets = [ "gfx1151" ];
-      hash = "sha256-VYvRjnNZpPE60wjpBVO1FbURMRRMg71sM5kBxiEkElk=";
+    }).overrideAttrs
-      postFetch = ''
+      (prevAttrs: {
-        echo -n "267f8af" > $out/COMMIT
+        src = prev.fetchFromGitHub {
-      '';
+          owner = "am17an";
-    };
+          repo = "llama.cpp";
-    npmDepsHash = "sha256-k62LIbyY2DXvs7XXbX0lNPiYxuYzeJUyQtS4eA+68f8=";
+          rev = "267f8afe857b7bd1a49e4fde9138ab0f7be36625";
-  });
+          hash = "sha256-VYvRjnNZpPE60wjpBVO1FbURMRRMg71sM5kBxiEkElk=";
+          postFetch = ''
+            echo -n "267f8af" > $out/COMMIT
+          '';
+        };
+        npmDepsHash = "sha256-k62LIbyY2DXvs7XXbX0lNPiYxuYzeJUyQtS4eA+68f8=";
+
+        buildInputs = (prevAttrs.buildInputs or [ ]) ++ [
+          channels.unstable.rocmPackages.rocwmma
+        ];
+
+        cmakeFlags = (prevAttrs.cmakeFlags or [ ]) ++ [
+          "-DGGML_HIP_ROCWMMA_FATTN=ON"
+          "-DGGML_HIP_GRAPHS=ON"
+        ];
+      });
 
   /*
     gnome-remote-desktop = channels.unstable.gnome-remote-desktop.overrideAttrs (prevAttrs: {