Skip to content

[auto] Update llama.cpp to latest version #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
May 23, 2025
Merged
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
7 changes: 4 additions & 3 deletions Package.swift
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

import PackageDescription

let llamaVersion = "b5443"
let llamaVersion = "b5465"

let package = Package(
name: "LocalLLMClient",
Expand Down Expand Up @@ -67,7 +67,7 @@ let package = Package(
name: "LocalLLMClientLlamaFramework",
url:
"https://github.com/ggml-org/llama.cpp/releases/download/\(llamaVersion)/llama-\(llamaVersion)-xcframework.zip",
checksum: "a461bae932c956371a3127f9230fa001c8c6b0cd2b930465772b24c3b274a323"
checksum: "f246f3833b1cff61384c221b826551c7c9b27954f3588ac3034cde01b452f22e"
),
.target(
name: "LocalLLMClientLlamaC",
Expand Down Expand Up @@ -101,5 +101,6 @@ let package = Package(
.product(name: "MLXLMCommon", package: "mlx-swift-examples"),
],
),
]
],
cxxLanguageStandard: .cxx20
)
2 changes: 1 addition & 1 deletion Sources/LocalLLMClientLlamaC/exclude/llama.cpp
Submodule llama.cpp updated 44 files
+4 −0 .editorconfig
+151 −128 .github/workflows/release.yml
+1 −0 README.md
+6 −6 common/arg.cpp
+1 −1 common/common.h
+120 −44 convert_hf_to_gguf.py
+13 −1 docs/multimodal.md
+6 −6 examples/retrieval/retrieval.cpp
+11 −0 ggml/include/ggml.h
+133 −6 ggml/src/ggml-cann/aclnn_ops.cpp
+9 −0 ggml/src/ggml-cann/ggml-cann.cpp
+1 −0 ggml/src/ggml-cpu/ggml-cpu.c
+107 −0 ggml/src/ggml-cpu/ops.cpp
+16 −0 ggml/src/ggml-cpu/vec.h
+24 −0 ggml/src/ggml-metal/ggml-metal.m
+37 −0 ggml/src/ggml-metal/ggml-metal.metal
+315 −155 ggml/src/ggml-opencl/ggml-opencl.cpp
+35 −3 ggml/src/ggml-sycl/ggml-sycl.cpp
+51 −4 ggml/src/ggml-vulkan/ggml-vulkan.cpp
+16 −1 ggml/src/ggml.c
+76 −7 gguf-py/gguf/constants.py
+1 −1 gguf-py/gguf/gguf_reader.py
+36 −7 gguf-py/gguf/gguf_writer.py
+62 −0 gguf-py/gguf/tensor_mapping.py
+5 −1 requirements/requirements-convert_hf_to_gguf.txt
+5 −1 requirements/requirements-convert_hf_to_gguf_update.txt
+2 −0 requirements/requirements-convert_lora_to_gguf.txt
+1 −1 src/llama-hparams.cpp
+12 −1 src/llama-hparams.h
+1 −0 src/llama-model.cpp
+13 −2 tools/mtmd/CMakeLists.txt
+37 −12 tools/mtmd/clip-impl.h
+261 −57 tools/mtmd/clip.cpp
+6 −0 tools/mtmd/clip.h
+93,468 −0 tools/mtmd/miniaudio.h
+855 −0 tools/mtmd/mtmd-audio.cpp
+62 −0 tools/mtmd/mtmd-audio.h
+21 −14 tools/mtmd/mtmd-cli.cpp
+27 −22 tools/mtmd/mtmd-helper.cpp
+290 −73 tools/mtmd/mtmd.cpp
+46 −17 tools/mtmd/mtmd.h
+54 −8 tools/server/server.cpp
+1 −1 tools/server/utils.hpp
+4 −2 tools/tts/tts.cpp
1 change: 1 addition & 0 deletions Sources/LocalLLMClientLlamaC/miniaudio.h
1 change: 1 addition & 0 deletions Sources/LocalLLMClientLlamaC/mtmd-audio.cpp
1 change: 1 addition & 0 deletions Sources/LocalLLMClientLlamaC/mtmd-audio.h