Skip to content

Tags: DrDub/llama.cpp

Tags

b3542

Toggle b3542's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
make : use C compiler to build metal embed object (ggml-org#8899)

* make : use C compiler to build metal embed object

* use rm + rmdir to avoid -r flag in rm

b3541

Toggle b3541's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
ggml-backend : fix async copy from CPU (ggml-org#8897)

* ggml-backend : fix async copy from CPU

* cuda : more reliable async copy, fix stream used when the devices are the same

b3540

Toggle b3540's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
[SYCL] Updated SYCL device filtering (ggml-org#8901)

* Updated device filter to depend on default_selector (fixes non-intel device issues)
* Small related update to example/sycl Readme

b3539

Toggle b3539's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
CUDA/HIP: fix tests/test-backend-ops (ggml-org#8896)

b3538

Toggle b3538's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
llama-bench : add support for getting cpu info on Windows (ggml-org#8824

)

* Add support for getting cpu info on Windows for llama_bench

* refactor

---------

Co-authored-by: slaren <[email protected]>

b3537

Toggle b3537's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
quantize : update usage comment in quantize.cpp (ggml-org#8889)

This commit updates the usage comment in quantize.cpp to reflect the
new name of the executable, which is llama-quantize.

b3536

Toggle b3536's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
typo correction (ggml-org#8891)

b3534

Toggle b3534's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
CUDA: fix padding logic for FP16/FP32 (ggml-org#8884)

b3532

Toggle b3532's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
cmake : Link vulkan-shaders-gen with pthreads (ggml-org#8835)

When using CMake to build with Vulkan support, compiling
vulkan-shaders-gen fails due to missing a CMakeLists.txt specification
to link vulkan-shaders-gen with the threading library, resulting in the
following error.

    [5/172] Linking CXX executable bin/vulkan-shaders-gen
    FAILED: bin/vulkan-shaders-gen
    : && /usr/bin/c++ ggml/src/vulkan-shaders/CMakeFiles/vulkan-shaders-gen.dir/vulkan-shaders-gen.cpp.o -o bin/vulkan-shaders-gen   && :
    ld: error: undefined symbol: pthread_create
    >>> referenced by vulkan-shaders-gen.cpp
    >>>               ggml/src/vulkan-shaders/CMakeFiles/vulkan-shaders-gen.dir/vulkan-shaders-gen.cpp.o:(std::__1::__libcpp_thread_create[abi:se180100](pthread**,
    >>>               void* (*)(void*), void*))
    c++: error: linker command failed with exit code 1 (use -v to see invocation)
    [6/172] Generating build details from Git
    -- Found Git: /usr/local/bin/git (found version "2.45.2")
    ninja: build stopped: subcommand failed.

Add the CMakeLists.txt specification to link vulkan-shaders-gen with the
threading library and fix the above error.

Fixes ggml-org#8834

b3531

Toggle b3531's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
[Vulkan] Fix compilation of `vulkan-shaders-gen` on w64devkit after `…

…e31a4f6` (ggml-org#8880)

* Fix compilation issue in `vulkan-shaders-gen`

ggml-org@e31a4f6 broke compilation on w64devkit. Including `algorithm` seems to fix that.

* Guard it under `#ifdef _WIN32`