Skip to content
This repository was archived by the owner on Jul 4, 2025. It is now read-only.

Update llama.cpp submodule to latest release b5381 #484

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update llama.cpp submodule to latest release b5381 #484

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion llama.cpp
Open in desktop
Submodule llama.cpp updated 53 files
+20 −2 convert_hf_to_gguf.py
+1 −1 docs/multimodal.md
+2 −2 ggml/src/ggml-cpu/CMakeLists.txt
+1 −0 ggml/src/ggml-cpu/kleidiai/kernels.h
+2 −0 ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
+1 −1 ggml/src/ggml-metal/ggml-metal.m
+5 −0 ggml/src/ggml-metal/ggml-metal.metal
+0 −2 ggml/src/ggml-opencl/ggml-opencl.cpp
+78 −89 ggml/src/ggml-vulkan/CMakeLists.txt
+184 −53 ggml/src/ggml-vulkan/ggml-vulkan.cpp
+17 −0 ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
+4 −3 ggml/src/ggml-vulkan/vulkan-shaders/flash_attn.comp
+506 −0 ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm1.comp
+12 −1 ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
+3 −0 gguf-py/gguf/constants.py
+1 −0 gguf-py/gguf/tensor_mapping.py
+1 −1 include/llama.h
+329 −121 scripts/compare-llama-bench.py
+1 −1 scripts/sync-ggml.last
+3 −0 src/llama-arch.cpp
+207 −33 src/llama-model.cpp
+13 −11 src/llama-quant.cpp
+2 −2 tools/batched-bench/batched-bench.cpp
+4 −3 tools/llama-bench/README.md
+44 −11 tools/llama-bench/llama-bench.cpp
+0 −35 tools/mtmd/CMakeLists.txt
+0 −44 tools/mtmd/README-quantize.md
+4 −3 tools/mtmd/README.md
+0 −53 tools/mtmd/android/adb_run.sh
+0 −8 tools/mtmd/android/build_64.sh
+0 −59 tools/mtmd/clip-quantize-cli.cpp
+0 −156 tools/mtmd/clip.cpp
+45 −81 tools/mtmd/clip.h
+0 −0 tools/mtmd/legacy-models/convert_image_encoder_to_gguf.py
+0 −0 tools/mtmd/legacy-models/glmedge-convert-image-encoder-to-gguf.py
+0 −0 tools/mtmd/legacy-models/glmedge-surgery.py
+0 −0 tools/mtmd/legacy-models/llava_surgery.py
+0 −0 tools/mtmd/legacy-models/llava_surgery_v2.py
+0 −0 tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py
+0 −0 tools/mtmd/legacy-models/minicpmv-surgery.py
+0 −591 tools/mtmd/llava.cpp
+0 −49 tools/mtmd/llava.h
+0 −636 tools/mtmd/qwen2vl-test.cpp
+13 −76 tools/quantize/quantize.cpp
+1 −1 tools/server/README.md
+ − tools/server/public/index.html.gz
+23 −12 tools/server/server.cpp
+12 −0 tools/server/tests/unit/test_completion.py
+1 −1 tools/server/utils.hpp
+8 −0 tools/server/webui/package-lock.json
+2 −1 tools/server/webui/package.json
+12 −1 tools/server/webui/src/components/ChatScreen.tsx
+4 −3 tools/server/webui/vite.config.ts
Loading