linalg/x86_64: add AVX-512 element-wise activations

.github/scripts/inject_wheel_sboms.py

@@ -0,0 +1,85 @@
+"""Inject CycloneDX + SPDX SBOMs into a wheel's `.dist-info/sboms/` per PEP 770.
+
+Reads the wheel, generates SBOMs from its unpacked contents via `syft`
+(which understands the `cargo-auditable` section embedded in the
+bundled Rust dylib), drops them into the wheel's metadata directory,
+and re-packs the wheel.  `wheel pack` regenerates RECORD so the new
+files are properly listed and hashed.
+
+Usage:  python inject_wheel_sboms.py wheel-1.whl wheel-2.whl ...
+        (in-place; replaces each input wheel with the SBOM-bearing one)
+
+Requires:  `syft` on PATH, and the `wheel` Python package installed.
+"""
+
+import shutil
+import subprocess
+import sys
+import tempfile
+from pathlib import Path
+
+
+def inject(wheel_path: Path) -> None:
+    wheel_path = wheel_path.resolve()
+    with tempfile.TemporaryDirectory() as tmp:
+        tmp = Path(tmp)
+        unpack_root = tmp / "unpacked"
+        repack_root = tmp / "repacked"
+        unpack_root.mkdir()
+        repack_root.mkdir()
+
+        subprocess.check_call(
+            [sys.executable, "-m", "wheel", "unpack", "-d", str(unpack_root), str(wheel_path)]
+        )
+
+        # `wheel unpack` writes one top-level dir named `<name>-<version>`
+        (unpacked,) = list(unpack_root.iterdir())
+        (dist_info,) = list(unpacked.glob("*.dist-info"))
+
+        sboms_dir = dist_info / "sboms"
+        sboms_dir.mkdir(exist_ok=True)
+
+        # syft scans the unpacked tree.  Its rust-audit-binary cataloger
+        # reads the `.dep-v0` ELF/Mach-O section that `cargo-auditable`
+        # embedded; the Python cataloger picks up METADATA.
+        subprocess.check_call(
+            [
+                "syft",
+                "scan",
+                f"dir:{unpacked}",
+                "--source-name",
+                unpacked.name,
+                "-o",
+                f"cyclonedx-json={sboms_dir / 'sbom.cdx.json'}",
+                "-o",
+                f"spdx-json={sboms_dir / 'sbom.spdx.json'}",
+            ]
+        )
+
+        # `wheel pack` rewrites RECORD with hashes for every file under
+        # `unpacked/`, including the two SBOMs we just added.
+        subprocess.check_call(
+            [sys.executable, "-m", "wheel", "pack", "-d", str(repack_root), str(unpacked)]
+        )
+
+        (repacked_wheel,) = list(repack_root.glob("*.whl"))
+        # Names should match; if `wheel pack` produced a different
+        # filename (e.g. build-tag difference), prefer the new name.
+        target = wheel_path.parent / repacked_wheel.name
+        if target != wheel_path:
+            wheel_path.unlink()
+        shutil.move(str(repacked_wheel), str(target))
+        print(f"injected SBOMs into {target.name}")
+
+
+def main(argv: list[str]) -> int:
+    if not argv:
+        print(__doc__, file=sys.stderr)
+        return 2
+    for w in argv:
+        inject(Path(w))
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main(sys.argv[1:]))

.github/workflows/binaries.yml

@@ -22,6 +22,11 @@ jobs:
     name: Upload Release Binaries
     permissions:
       contents: write
+      # OIDC + attestations: cryptographically sign each released .tgz
+      # against its SBOMs via GitHub's attestation store.  Anyone can
+      # then verify with `gh attestation verify <tgz> --owner sonos`.
+      id-token: write
+      attestations: write
     strategy:
       fail-fast: false
       matrix:
@@ -98,15 +103,59 @@ jobs:
             export CARGO_TARGET_${RUST_TRIPLE_ENV}_LINKER=$TARGET_CC
           fi
 
-          cargo build --target ${target} --release -p tract-cli
+          # cargo-auditable wraps `cargo build` to embed the resolved
+          # dependency graph into the binary so consumers can recover
+          # the SBOM directly from the binary via `cargo audit bin`.
+          cargo install --locked cargo-auditable --version 0.7.0
+          cargo auditable build --target ${target} --release -p tract-cli --locked
           mkdir tract-$name
           cp target/${target}/release/tract tract-${name}
           tar czf tract-${name}.tgz tract-${name}
 
+      - name: Generate CycloneDX SBOM
+        uses: anchore/sbom-action@e22c389904149dbc22b58101806040fa8d37a610 # v0.24.0
+        with:
+          path: .
+          format: cyclonedx-json
+          artifact-name: tract-${{ matrix.target }}-${{ steps.version.outputs.value }}.cdx.json
+          output-file: tract-${{ matrix.target }}-${{ steps.version.outputs.value }}.cdx.json
+          upload-artifact: false
+          upload-release-assets: false
+
+      - name: Generate SPDX SBOM
+        uses: anchore/sbom-action@e22c389904149dbc22b58101806040fa8d37a610 # v0.24.0
+        with:
+          path: .
+          format: spdx-json
+          artifact-name: tract-${{ matrix.target }}-${{ steps.version.outputs.value }}.spdx.json
+          output-file: tract-${{ matrix.target }}-${{ steps.version.outputs.value }}.spdx.json
+          upload-artifact: false
+          upload-release-assets: false
+
+      - name: Attest build provenance
+        uses: actions/attest-build-provenance@a2bbfa25375fe432b6a289bc6b6cd05ecd0c4c32 # v4.1.0
+        with:
+          subject-path: tract-${{ matrix.target }}-${{ steps.version.outputs.value }}.tgz
+
+      - name: Attest release tarball with CycloneDX SBOM
+        uses: actions/attest-sbom@c604332985a26aa8cf1bdc465b92731239ec6b9e # v4.1.0
+        with:
+          subject-path: tract-${{ matrix.target }}-${{ steps.version.outputs.value }}.tgz
+          sbom-path: tract-${{ matrix.target }}-${{ steps.version.outputs.value }}.cdx.json
+
+      - name: Attest release tarball with SPDX SBOM
+        uses: actions/attest-sbom@c604332985a26aa8cf1bdc465b92731239ec6b9e # v4.1.0
+        with:
+          subject-path: tract-${{ matrix.target }}-${{ steps.version.outputs.value }}.tgz
+          sbom-path: tract-${{ matrix.target }}-${{ steps.version.outputs.value }}.spdx.json
+
       - name: Upload asset
         uses: softprops/action-gh-release@b4309332981a82ec1c5618f44dd2e27cc8bfbfda # v3
         with:
-          files: tract-${{matrix.target}}-${{ steps.version.outputs.value }}.tgz
+          files: |
+            tract-${{matrix.target}}-${{ steps.version.outputs.value }}.tgz
+            tract-${{matrix.target}}-${{ steps.version.outputs.value }}.cdx.json
+            tract-${{matrix.target}}-${{ steps.version.outputs.value }}.spdx.json
           name: ${{ steps.version.outputs.value }}
           tag_name: v${{ steps.version.outputs.value }}
         env:

.github/workflows/wheels.yml

@@ -63,6 +63,18 @@ jobs:
           timeout_seconds: 54000 # 15 hours :/
           command: uvx cibuildwheel --output-dir wheelhouse api/py
 
+      - name: Install syft
+        uses: anchore/sbom-action/download-syft@e22c389904149dbc22b58101806040fa8d37a610 # v0.24.0
+
+      - name: Inject CycloneDX + SPDX SBOMs into wheels (PEP 770)
+        shell: bash
+        run: |
+          set -ex
+          uv pip install --system wheel
+          for w in wheelhouse/*.whl ; do
+            python .github/scripts/inject_wheel_sboms.py "$w"
+          done
+
       - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         with:
           name: wheels-${{github.run_id}}-${{matrix.os}}

.gitignore

@@ -2,7 +2,6 @@ target
 **/*.rs.bk
 *.rustfmt
 *.back
-Cargo.lock
 examples/data
 .idea
 .cached/**

CHANGELOG.md

@@ -3,10 +3,12 @@
 ### CPU / linalg
 
 - **ARM SME backend (ARMv9.2-A).** New `linalg/arm64/sme` module provides SME GEMM (Phase 1) and SME2 GEMV (`sme_mmv_f32_64x1`, Phase 2A) micro-kernels for Apple M4+, Cortex-X4, and other ARMv9.2-A+ chips. Dispatch is gated on a 512-bit streaming vector length at runtime; SME2 assembler detection skips kernels when the assembler lacks support. Force via `TRACT_CPU_AARCH64_KIND=applem` (or `generic` to disable).
+- **ARMv9 SVE**: f32/f16 GEMM+GEMV and int8→i32 GEMM+GEMV kernels
 - **Apple AMX: shape-aware dispatch.** AMX kernel selection is now M/N/K-aware at runtime, yielding 5–43% wins across canary models.
 - **NEON element-wise kernels.** `HardSwish`, `SiLU`, and `GELU` get dedicated aarch64 NEON kernels wired as single graph ops.
 - **x86_64.** M-aware kernel picker; AVX-512 GEMM routed to the 16×8 / 32×5 / 32×6 kernels.
 - **WASM SIMD.** Relaxed-SIMD FMA in all MMM kernels; 32×1 GEMV kernel (8 v128 accumulators, 8-way ILP); vectorised sigmoid and tanh; `rustfft wasm_simd` enabled. Low-accumulator MMM paths recover 8–23% under `+relaxed-simd`; M-band GEMV dispatch woken up (30–37% on small-M). `Executor::RayonGlobal` for `wasm-bindgen-rayon`.
+- **WASM**: relaxed-dot int8 fast path + PackedI8K4 + SIMD int8 matmul.
 - **Multithreaded GEMM.** TLS borrow and sync hoisted out of the per-tile inner loop; 2D chunked dispatch with a small-MMM threshold avoids rayon overhead on small operands.
 - **im2col.** Contiguous-x fast path for valid (zero-padding, unit stride) convolutions; grouped lazy im2col extended; depthwise convolutions excluded from lazy im2col path; N=1/2/3 zone dispatch for depthwise.
 - **General.** Same-shape fast path in `BinMiniOp::generic_eval`; `rbytes=96/128` fast paths for mn-major packing.
@@ -17,6 +19,8 @@
 
 - `Resize`: `pytorch_half_pixel` coordinate transformer.
 - `Reshape` with 0-dims and rank change fixed (issue #2104).
+-  Support for GroupQueryAttention, MultiHeadAttention, MatMulNBits (4-bit), SkipLayerNormalization, SimplifiedLayerNormalization, BiasGelu / FastGelu /
+  QuickGelu, LpNormalization, MeanVarianceNormalization, GroupNormalization, RotaryEmbedding, opset-24 Attention, Swish, Mish, Gelu, RMSNormalization.
 
 ### NNEF
 
@@ -26,7 +30,7 @@
 ### Pulse for chunked attention layers (experimental)
 
 - **`pulse::Blockify` rewrite pass.** Translates block-diagonal multi-time-axis subgraphs into chunk-parallel form: recognises quadratic sections (EinSum terminators, `DiagGather` initiators, banded masks, Softmax body chains) and rewrites each into a per-chunk section. Covered by ex01–ex10 synthetic harness cases.
-- **`DiagGather` op** (moved from `transformers` into `core`): causal skew-trick gather with ROI-driven narrowing and re-anchoring.
+- **`DiagGather` op**: causal skew-trick gather with ROI-driven narrowing and re-anchoring.
 - **`WindowOnAxis` op**: windowed gather over the streaming axis with configurable pad value.
 - **`AxisOp::Reshape` pulsifier**: auto-inserts alignment `Delay` on streaming-axis size change.
 - Stream-axis LCM merge + slope-based per-pulse sizing for `Range`.
@@ -53,7 +57,7 @@
 - `doc/symbolic-shapes.md`: TDim, Symbol, and how to bind them.
 - `doc/op.md`: working with a `Tensor`'s data.
 - `doc/cli-recipe.md`: `--audit-json`, `--save-outputs`, timing pitfalls, environment-variable table.
-- `README.md`: refreshed — current backends, modern examples table, Python bindings section, torch-to-nnef pointer.
+- `README.md`: refreshed — current runtimes, modern examples table, Python bindings section, torch-to-nnef pointer.
 
 # 0.23.0-dev.5 - 2026-04-22
 
@@ -146,7 +150,7 @@
 - **`into_tract()` renamed to `into_model()`** in all API layers.
 - **`DatumType` variant names shortened** — the `TRACT_DATUM_TYPE_` prefix is dropped (C API).
 - **Deprecated state methods removed**: `init_states()`, `state_initializers`, and the `n_states` parameter are gone from `State` trait and `RunTensors`.
-- **Python**: `concretize_symbols` and `pulse` methods replaced by typed transform classes; `TransformSpec` is now an abstract base class.
+- **Python**: `set_symbols` and `pulse` methods replaced by typed transform classes; `TransformSpec` is now an abstract base class.
 
 ### Improvements