Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 30 additions & 0 deletions manifests/g/ggml/llamacpp/b7898/ggml.llamacpp.installer.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
# Created with komac v2.11.2
# yaml-language-server: $schema=https://aka.ms/winget-manifest.installer.1.9.0.schema.json

PackageIdentifier: ggml.llamacpp
PackageVersion: b7898
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: 2026-01-31
ArchiveBinariesDependOnPath: true
Installers:
- Architecture: x64
InstallerUrl: https://github.com/ggml-org/llama.cpp/releases/download/b7898/llama-b7898-bin-win-vulkan-x64.zip
InstallerSha256: 0AB5E72A688BD37E21871C913A3B159851284E24B64F8FA1E6F90BF620905624
ManifestType: installer
ManifestVersion: 1.9.0
65 changes: 65 additions & 0 deletions manifests/g/ggml/llamacpp/b7898/ggml.llamacpp.locale.en-US.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,65 @@
# Created with komac v2.11.2
# yaml-language-server: $schema=https://aka.ms/winget-manifest.defaultLocale.1.9.0.schema.json

PackageIdentifier: ggml.llamacpp
PackageVersion: b7898
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: |-
ggml-hexagon: flash-attention and reduce-sum optimizations (#19141)
- wip
- ggml-hexagon: add vectorized dot product function for FP32 and FP16 accumulation
- ggml-hexagon: optimize dot product functions for FP16 and FP32 with new vectorized implementations
- wip
- ggml-hexagon: optimize hvx_vec_dump_f32_n and hvx_vec_reduce_sum_qf32x2 functions for improved performance
- ggml-hexagon: refactor dot product functions to use a common loading function for improved readability
- optimize vector dot product functions to use unified reduction for improved performance
- wip
- ggml-hexagon: add vectorized dot product function for FP32 and FP16 accumulation
- ggml-hexagon: optimize dot product functions for FP16 and FP32 with new vectorized implementations
- wip
- ggml-hexagon: optimize hvx_vec_dump_f32_n and hvx_vec_reduce_sum_qf32x2 functions for improved performance
- ggml-hexagon: refactor dot product functions to use a common loading function for improved readability
- optimize vector dot product functions to use unified reduction for improved performance
- hexagon: optimize reduce-sum for v75+
- hexagon: always keep row_sums in sf/fp32
- ggml-hexagon: enhance directory checks for HEXAGON_SDK_ROOT and HEXAGON_TOOLS_ROOT
- fix compiling error after rebase
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- 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/b7898
Documentations:
- DocumentLabel: Wiki
DocumentUrl: https://github.com/ggml-org/llama.cpp/wiki
ManifestType: defaultLocale
ManifestVersion: 1.9.0
8 changes: 8 additions & 0 deletions manifests/g/ggml/llamacpp/b7898/ggml.llamacpp.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
# Created with komac v2.11.2
# yaml-language-server: $schema=https://aka.ms/winget-manifest.version.1.9.0.schema.json

PackageIdentifier: ggml.llamacpp
PackageVersion: b7898
DefaultLocale: en-US
ManifestType: version
ManifestVersion: 1.9.0