Skip to content

Bump skainet from 0.29.1 to 0.30.0#134

Closed
dependabot[bot] wants to merge 1 commit into
developfrom
dependabot/gradle/skainet-0.30.0
Closed

Bump skainet from 0.29.1 to 0.30.0#134
dependabot[bot] wants to merge 1 commit into
developfrom
dependabot/gradle/skainet-0.30.0

Conversation

@dependabot

@dependabot dependabot Bot commented on behalf of github Jun 15, 2026

Copy link
Copy Markdown
Contributor

Bumps skainet from 0.29.1 to 0.30.0.
Updates sk.ainet.core:skainet-lang-core from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-lang-core's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-lang-models from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-lang-models's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-model-yolo from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-model-yolo's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-lang-dag from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-lang-dag's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-compile-core from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-compile-core's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-compile-dag from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-compile-dag's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-backend-cpu from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-backend-cpu's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-data-api from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-data-api's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-data-basic from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-data-basic's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-io-core from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-io-core's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-io-gguf from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-io-gguf's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Updates sk.ainet.core:skainet-io-onnx from 0.29.1 to 0.30.0

Changelog

Sourced from sk.ainet.core:skainet-io-onnx's changelog.

[0.30.0] - 2026-06-13

Added

  • First-class Q5_K packed matmul. New TensorEncoding.Q5_K, Q5_KTensorData / Q5_KBlockTensorData (256-element / 176-byte super-blocks with the qh 5th-bit plane), and a Q5KMatmulKernel SPI. Implementations: scalar reference (commonMain → Kotlin/Native, JS, Wasm), JVM Panama Vector, and native-C (FFM). Wired into DefaultCpuOps packed-quant matmul dispatch + lazy transpose, registered via KernelRegistry, and added to the GGUF StreamingGgufParametersLoader (Q5_K + Q6_K packed branches). Q5_K weights stay packed and dequantize inside the matmul, matching the existing Q4_K/Q6_K path. (PR #734)
  • ARM NEON kernels for the native CPU backend. Hand-written NEON paths for fp32, q8_0, q4k, and q5k matmul (shared skainet_simd.h), behind #if __ARM_NEON so x86 keeps its -O3 -ffast-math auto-vectorized scalar path. The native CMake build adds an aarch64 branch (-march=armv8.2-a+fp16+dotprod; no +i8mm — Cortex-A55 lacks it) and an opt-in -PcrossArm64 cross-compile with a toolchain file. (PR #734)
  • Kotlin/Native consumption of the C kernels via cinterop. skainet-backend-native-cpu now builds a static archive (libskainet_kernels.a) alongside the shared lib and adds linuxX64 + linuxArm64 targets with a cinterop .def, shared nativeMain NativeKn*MatmulKernel wrappers, and a NativeKnKernelProvider (+ installNativeKernels()). On-device Kotlin/Native binaries can now reach the same hand-tuned C/NEON kernels the JVM uses via FFM. (PR #734)
Commits
  • 4838eea docs: prepare 0.30.0 release (CHANGELOG, README, version pins, kernel matrix)
  • b75b9b7 build: bump version 0.29.1 -> 0.30.0 (Q5_K + NEON + K/N cinterop)
  • 92485f2 Merge pull request #734 from SKaiNET-developers/feature/q5k-neon-kernels
  • 587d59b feat(backend-native-cpu): add linuxArm64 (board) K/N target
  • 1b6f7f6 feat(backend-native-cpu): K/N KernelProvider over the cinterop kernels
  • 5814200 feat(backend-native-cpu): Kotlin/Native cinterop to the C/NEON kernels
  • 0101041 feat(backend): first-class Q5_K packed matmul + ARM NEON kernels
  • 6d85369 Merge pull request #732 from SKaiNET-developers/chore/security-policy-336
  • e7b5033 Merge pull request #728 from SKaiNET-developers/release/0.29.1
  • 0f83e37 docs: add SECURITY.md security policy (#336)
  • Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

  • @dependabot rebase will rebase this PR
  • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
  • @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
  • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
  • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
  • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot
Bump skainet from 0.29.1 to 0.30.0
77327e4 
Bumps `skainet` from 0.29.1 to 0.30.0.

Updates `sk.ainet.core:skainet-lang-core` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-lang-models` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-model-yolo` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-lang-dag` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-compile-core` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-compile-dag` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-backend-cpu` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-data-api` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-data-basic` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-io-core` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-io-gguf` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

Updates `sk.ainet.core:skainet-io-onnx` from 0.29.1 to 0.30.0
- [Changelog](https://github.com/SKaiNET-developers/SKaiNET/blob/develop/CHANGELOG.md)
- [Commits](SKaiNET-developers/SKaiNET@0.29.1...0.30.0)

---
updated-dependencies:
- dependency-name: sk.ainet.core:skainet-lang-core
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-lang-models
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-model-yolo
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-lang-dag
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-compile-core
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-compile-dag
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-backend-cpu
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-data-api
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-data-basic
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-io-core
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-io-gguf
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
- dependency-name: sk.ainet.core:skainet-io-onnx
  dependency-version: 0.30.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
@dependabot dependabot Bot added dependencies Pull requests that update a dependency file java Pull requests that update java code labels Jun 15, 2026
@dependabot @github

dependabot Bot commented on behalf of github Jun 16, 2026

Copy link
Copy Markdown
Contributor Author

Superseded by #135.

@dependabot dependabot Bot closed this Jun 16, 2026
@dependabot dependabot Bot deleted the dependabot/gradle/skainet-0.30.0 branch June 16, 2026 04:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

dependencies Pull requests that update a dependency file java Pull requests that update java code

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

0 participants