New version: ggml.llamacpp version b8184

Author: ggml-bot-2

manifests/g/ggml/llamacpp/b8184/ggml.llamacpp.installer.yaml

@@ -0,0 +1,30 @@
+# Created with komac v2.15.0
+# yaml-language-server: $schema=https://aka.ms/winget-manifest.installer.1.12.0.schema.json
+
+PackageIdentifier: ggml.llamacpp
+PackageVersion: b8184
+InstallerType: zip
+NestedInstallerType: portable
+NestedInstallerFiles:
+- RelativeFilePath: llama-batched-bench.exe
+- RelativeFilePath: llama-bench.exe
+- RelativeFilePath: llama-cli.exe
+- RelativeFilePath: llama-gguf-split.exe
+- RelativeFilePath: llama-imatrix.exe
+- RelativeFilePath: llama-mtmd-cli.exe
+- RelativeFilePath: llama-perplexity.exe
+- RelativeFilePath: llama-quantize.exe
+- RelativeFilePath: llama-server.exe
+- RelativeFilePath: llama-tokenize.exe
+- RelativeFilePath: llama-tts.exe
+Dependencies:
+  PackageDependencies:
+  - PackageIdentifier: Microsoft.VCRedist.2015+.x64
+ReleaseDate: 2026-03-01
+ArchiveBinariesDependOnPath: true
+Installers:
+- Architecture: x64
+  InstallerUrl: https://github.com/ggml-org/llama.cpp/releases/download/b8184/llama-b8184-bin-win-vulkan-x64.zip
+  InstallerSha256: 2D60828F4B90BDD1E93698837C163B54F40E7D682E8018DC40F52EB444C3CCEB
+ManifestType: installer
+ManifestVersion: 1.12.0

manifests/g/ggml/llamacpp/b8184/ggml.llamacpp.locale.en-US.yaml

@@ -0,0 +1,54 @@
+# Created with komac v2.15.0
+# yaml-language-server: $schema=https://aka.ms/winget-manifest.defaultLocale.1.12.0.schema.json
+
+PackageIdentifier: ggml.llamacpp
+PackageVersion: b8184
+PackageLocale: en-US
+Publisher: ggml
+PublisherUrl: https://github.com/ggml-org
+PublisherSupportUrl: https://github.com/ggml-org/llama.cpp/issues
+PackageName: llama.cpp
+PackageUrl: https://github.com/ggml-org/llama.cpp
+License: MIT
+LicenseUrl: https://github.com/ggml-org/llama.cpp/blob/HEAD/LICENSE
+ShortDescription: LLM inference in C/C++
+Tags:
+- ggml
+- llama
+ReleaseNotes: |-
+  vulkan: improve partial offloading performance on AMD (#19976)
+  - vulkan: fix and enable cpy_tensor_async function
+  - use transfer_queue for async transfers on AMD, synchronize with timeline semaphore
+  - update offload_op logic
+  - fix missing transfer submission
+  - disable async transfer queue on AMD GCN
+  - revert op batch size change
+  - fix cpy_tensor_async checks
+  macOS/iOS:
+  - macOS Apple Silicon (arm64)
+  - macOS Intel (x64)
+  - iOS XCFramework
+  Linux:
+  - Ubuntu x64 (CPU)
+  - Ubuntu x64 (Vulkan)
+  - Ubuntu x64 (ROCm 7.2)
+  - Ubuntu s390x (CPU)
+  Windows:
+  - Windows x64 (CPU)
+  - Windows arm64 (CPU)
+  - Windows x64 (CUDA 12) - CUDA 12.4 DLLs
+  - Windows x64 (CUDA 13) - CUDA 13.1 DLLs
+  - Windows x64 (Vulkan)
+  - Windows x64 (SYCL)
+  - Windows x64 (HIP)
+  openEuler:
+  - openEuler x86 (310p)
+  - openEuler x86 (910b, ACL Graph)
+  - openEuler aarch64 (310p)
+  - openEuler aarch64 (910b, ACL Graph)
+ReleaseNotesUrl: https://github.com/ggml-org/llama.cpp/releases/tag/b8184
+Documentations:
+- DocumentLabel: Wiki
+  DocumentUrl: https://github.com/ggml-org/llama.cpp/wiki
+ManifestType: defaultLocale
+ManifestVersion: 1.12.0

manifests/g/ggml/llamacpp/b8184/ggml.llamacpp.yaml

@@ -0,0 +1,8 @@
+# Created with komac v2.15.0
+# yaml-language-server: $schema=https://aka.ms/winget-manifest.version.1.12.0.schema.json
+
+PackageIdentifier: ggml.llamacpp
+PackageVersion: b8184
+DefaultLocale: en-US
+ManifestType: version
+ManifestVersion: 1.12.0