Skip to content

[pull] master from ggml-org:master #80

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.

Sign up for GitHub

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
pull merged 6 commits into from
May 20, 2026
Merged

[pull] master from ggml-org:master #80

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
871b0b7
snapdragon: update toolchain to v0.6 (#23369)
max-krasnyansky May 20, 2026
57ebaf4
metal : optimize pad + cpy (#23354)
ggerganov May 20, 2026
585080d
fix: Div wrapper no pointer events on hidden (#23390)
allozaur May 20, 2026
5028447
ui: Refactor `isMobile` as reactive value in `viewport` store (#23330)
allozaur May 20, 2026
7e50ef7
docker : copy conversion files (#23370)
CISC May 20, 2026
e2b129e
mtmd: fit_params now take into account mmproj (#21489)
ngxson May 20, 2026
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
1 change: 1 addition & 0 deletions .devops/cann.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,7 @@ RUN mkdir -p /app/lib && \
RUN mkdir -p /app/full && \
cp build/bin/* /app/full/ && \
cp *.py /app/full/ && \
cp -r conversion /app/full/ && \
cp -r gguf-py /app/full/ && \
cp -r requirements /app/full/ && \
cp requirements.txt /app/full/
Expand Down
1 change: 1 addition & 0 deletions .devops/cpu.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@ RUN mkdir -p /app/lib && \
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
Expand Down
1 change: 1 addition & 0 deletions .devops/cuda.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ RUN mkdir -p /app/lib && \
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
Expand Down
1 change: 1 addition & 0 deletions .devops/intel.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ RUN mkdir -p /app/lib && \
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
Expand Down
1 change: 1 addition & 0 deletions .devops/musa.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@ RUN mkdir -p /app/lib && \
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
Expand Down
1 change: 1 addition & 0 deletions .devops/openvino.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,7 @@ RUN mkdir -p /app/lib && \
RUN mkdir -p /app/full \
&& cp build/ReleaseOV/bin/* /app/full/ \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
Expand Down
1 change: 1 addition & 0 deletions .devops/rocm.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,7 @@ RUN mkdir -p /app/lib \
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
Expand Down
9 changes: 6 additions & 3 deletions .devops/s390x.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@ RUN --mount=type=cache,target=/root/.ccache \

COPY *.py /opt/llama.cpp/bin
COPY .devops/tools.sh /opt/llama.cpp/bin
COPY conversion /opt/llama.cpp/conversion

COPY gguf-py /opt/llama.cpp/gguf-py
COPY requirements.txt /opt/llama.cpp/gguf-py
Expand All @@ -47,9 +48,10 @@ COPY requirements /opt/llama.cpp/gguf-py/requirements
FROM scratch AS collector

# Copy llama.cpp binaries and libraries
COPY --from=build /opt/llama.cpp/bin /llama.cpp/bin
COPY --from=build /opt/llama.cpp/lib /llama.cpp/lib
COPY --from=build /opt/llama.cpp/gguf-py /llama.cpp/gguf-py
COPY --from=build /opt/llama.cpp/bin /llama.cpp/bin
COPY --from=build /opt/llama.cpp/lib /llama.cpp/lib
COPY --from=build /opt/llama.cpp/gguf-py /llama.cpp/gguf-py
COPY --from=build /opt/llama.cpp/conversion /llama.cpp/conversion


### Base image
Expand Down Expand Up @@ -107,6 +109,7 @@ RUN curl https://sh.rustup.rs -sSf | bash -s -- -y

COPY --from=collector /llama.cpp/bin /app
COPY --from=collector /llama.cpp/gguf-py /app/gguf-py
COPY --from=collector /llama.cpp/conversion /app/conversion

RUN pip install --no-cache-dir --break-system-packages \
-r /app/gguf-py/requirements.txt
Expand Down
1 change: 1 addition & 0 deletions .devops/vulkan.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ RUN mkdir -p /app/lib && \
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r conversion /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/build-and-test-snapdragon.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ jobs:
android-ndk-snapdragon:
runs-on: ubuntu-latest
container:
image: 'ghcr.io/snapdragon-toolchain/arm64-android:v0.3'
image: 'ghcr.io/snapdragon-toolchain/arm64-android:v0.6'
defaults:
run:
shell: bash
Expand Down Expand Up @@ -61,7 +61,7 @@ jobs:
linux-iot-snapdragon:
runs-on: ubuntu-latest
container:
image: 'ghcr.io/snapdragon-toolchain/arm64-linux:v0.1'
image: 'ghcr.io/snapdragon-toolchain/arm64-linux:v0.6'
defaults:
run:
shell: bash
Expand Down
8 changes: 4 additions & 4 deletions docs/backend/snapdragon/CMakeUserPresets.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,8 +10,8 @@
"ANDROID_ABI": "arm64-v8a",
"ANDROID_PLATFORM": "android-31",
"CMAKE_TOOLCHAIN_FILE": "$env{ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake",
"CMAKE_C_FLAGS": "-march=armv8.7a+fp16 -fvectorize -ffp-model=fast -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_CXX_FLAGS": "-march=armv8.7a+fp16 -fvectorize -ffp-model=fast -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_C_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_CXX_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_C_FLAGS_RELEASE": "-O3 -DNDEBUG",
"CMAKE_CXX_FLAGS_RELEASE": "-O3 -DNDEBUG",
"CMAKE_C_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
Expand Down Expand Up @@ -59,8 +59,8 @@
"toolset": { "value": "host=x86_64", "strategy": "external" },
"cacheVariables": {
"CMAKE_TOOLCHAIN_FILE": "cmake/arm64-linux-clang.cmake",
"CMAKE_C_FLAGS": "-march=armv8 -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_CXX_FLAGS": "-march=armv8 -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_C_FLAGS": "-march=armv8.2a+fp16+dotprod -fvectorize -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_CXX_FLAGS": "-march=armv8.2a+fp16+dotprod -fvectorize -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_C_FLAGS_RELEASE": "-O3 -DNDEBUG",
"CMAKE_CXX_FLAGS_RELEASE": "-O3 -DNDEBUG",
"CMAKE_C_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
Expand Down
2 changes: 1 addition & 1 deletion docs/backend/snapdragon/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ This image includes Android NDK, OpenCL SDK, Hexagon SDK, CMake, etc.
This method works on Linux, macOS, and Windows. macOS and Windows users should install Docker Desktop.

```
~/src/llama.cpp$ docker run -it -u $(id -u):$(id -g) --volume $(pwd):/workspace --platform linux/amd64 ghcr.io/snapdragon-toolchain/arm64-android:v0.3
~/src/llama.cpp$ docker run -it -u $(id -u):$(id -g) --volume $(pwd):/workspace --platform linux/amd64 ghcr.io/snapdragon-toolchain/arm64-android:v0.6
[d]/> cd /workspace
```

Expand Down
8 changes: 7 additions & 1 deletion ggml/src/ggml-metal/ggml-metal-device.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1897,7 +1897,11 @@ ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_pad(ggml_metal_l
char base[256];
char name[256];

snprintf(base, 256, "kernel_pad_%s", ggml_type_name(op->src[0]->type));
// note: this is slower
//const bool is_c4 = op->src[0]->ne[0] % 4 == 0 && op->ne[0] % 4 == 0;
const bool is_c4 = false;

snprintf(base, 256, "kernel_pad_%s%s", ggml_type_name(op->src[0]->type), is_c4 ? "_4" : "");
snprintf(name, 256, "%s", base);

ggml_metal_pipeline_with_params res = ggml_metal_library_get_pipeline(lib, name);
Expand All @@ -1907,6 +1911,8 @@ ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_pad(ggml_metal_l

res = ggml_metal_library_compile_pipeline(lib, base, name, nullptr);

res.c4 = is_c4;

return res;
}

Expand Down
17 changes: 11 additions & 6 deletions ggml/src/ggml-metal/ggml-metal-ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -816,9 +816,7 @@ int ggml_metal_op_unary(ggml_metal_op_t ctx, int idx) {
ggml_metal_encoder_dispatch_threadgroups(enc, n, 1, 1, 1, 1, 1);
} else {
const int nth_max = MIN(256, ggml_metal_pipeline_max_theads_per_threadgroup(pipeline));

const int nth = MIN(args.ne00, nth_max);

const int nk0 = (args.ne00 + nth - 1)/nth;

ggml_metal_encoder_dispatch_threadgroups(enc, nk0*ne01, ne02, ne03, nth, 1, 1);
Expand Down Expand Up @@ -1863,7 +1861,7 @@ int ggml_metal_op_cpy(ggml_metal_op_t ctx, int idx) {
nk0 = ne00/ggml_blck_size(op->type);
}

int nth = std::min<int>(nk0, ggml_metal_pipeline_max_theads_per_threadgroup(pipeline));
int nth = std::min<int>(nk0*ne01, 256);

// when rows are small, we can batch them together in a single threadgroup
int nrptg = 1;
Expand All @@ -1874,7 +1872,7 @@ int ggml_metal_op_cpy(ggml_metal_op_t ctx, int idx) {
nrptg = (nth + nk0 - 1)/nk0;
nth = nk0;

if (nrptg*nth > ggml_metal_pipeline_max_theads_per_threadgroup(pipeline)) {
if (nrptg*nth > 256) {
nrptg--;
}
}
Expand Down Expand Up @@ -4039,14 +4037,21 @@ int ggml_metal_op_pad(ggml_metal_op_t ctx, int idx) {

auto pipeline = ggml_metal_library_get_pipeline_pad(lib, op);

const int nth = std::min(1024, ne0);
if (pipeline.c4) {
args.ne00 = ne00/4;
args.ne0 = ne0/4;
}

const int nth_max = MIN(64, ggml_metal_pipeline_max_theads_per_threadgroup(pipeline));
const int nth = MIN(args.ne0, nth_max);
const int nk0 = (args.ne0 + 1024 - 1)/1024; // note: 1024 is hardcoded in the kernel!

ggml_metal_encoder_set_pipeline(enc, pipeline);
ggml_metal_encoder_set_bytes (enc, &args, sizeof(args), 0);
ggml_metal_encoder_set_buffer (enc, ggml_metal_get_buffer_id(op->src[0]), 1);
ggml_metal_encoder_set_buffer (enc, ggml_metal_get_buffer_id(op), 2);

ggml_metal_encoder_dispatch_threadgroups(enc, ne1, ne2, ne3, nth, 1, 1);
ggml_metal_encoder_dispatch_threadgroups(enc, nk0*ne1, ne2, ne3, nth, 1, 1);

return 1;
}
Expand Down
Loading
Loading