* weight format to nz for 310p
* remove quant weight format to nz
* clean code
* fix
* make the conditions for converting weights to NZ format consistent
* clean code
* ggml/ggml-vulkan/test-backend-ops: adds CONV_2D for Vulkan
* ggml-vulkan: adds f32 scalar shader to compute 2D convolution directly
with gemm (no need for im2col),
* test-backend-ops: adds test_case_ref to check the validity/performance of ops
against reference implementations having different graphs, adds tests
* * Performance fixes: minimized branch divergence, uses collectives to
eliminate redundant calculation, macros removed.
* Kernel shared memory size check
* Updates test-backend-ops to support graphs for performance
measurement.
* * Apple/Win32 compile errors fixed
* Subgroup size used to determine tile size -> fixes llvmpipe errors.
* Collectives disabled by default.
* Intel support is disabled as the performance is poor.
* Conv2d enabled for Intel with disabled collectives, disabled for Apple
* test-backend-ops modifications are reverted
* Trailing spaces and missing override fixed.
* Triggering pipeline relaunch.
* Code formatted with .clang-format.
* CMake config: Create target only once
Fix error on repeated find_package(ggml).
For simplicity, check only for the top-level ggml::ggml.
* CMake config: Add CUDA link libs
* CMake config: Add OpenCL link libs
* CMake config: Use canonical find_dependency
Use set and append to control link lib variables.
Apply more $<LINK_ONLY...>.
* CMake config: Wire OpenMP dependency
This commit removes the inclusion of `<cstdlib>`.
The motivation for this change is that this source file does not seem to
use any functions from this header and the comment about `qsort` is a
little misleading/confusing.
* This commit allows for the building of a static xcframework by adding a
BUILD_STATIC_XCFRAMEWORK option. When enabled, the build-xcframework.sh
script builds a self-contained static whisper.xcframework.
The motivation for this change is so that command line binaries can link
whisper.cpp without forcing users to install the whisper.xcframework
separately.
* Update build-xcframework.sh
Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
* Address reviewer feedback: remove extra indentation around static xcframework creation.
* squash! Address reviewer feedback: remove extra indentation around static xcframework creation.
Fix whitespaces.
---------
Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
This commit adds a note to the README files of the WASM examples
about the `WHISPER_WASM_SINGLE_FILE` option.
The motivation for this is that currently this option is not documented
and might be surprising to users who expect a separate .wasm file to be
generated.
Refs: https://github.com/ggml-org/whisper.cpp/issues/3290
This commit adds specific paths to the GitHub Actions workflow file
`.github/workflows/build.yml`.
The motivation for this to avoid unnecessary builds when unrelated files
are changed, which can save resources and time during the CI process.
Refs: https://github.com/ggml-org/whisper.cpp/issues/3285
This commit fixes Go bindings build failure for Mac OS X (15.1) which is currently failing.
Co-authored-by: Chaitanya Bayapuneni <bvk@mini.cinnamon-interval.ts.net>
* Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs
Gemma3n uses Matrix-Matrix addition as part of their input processing,
wrongly triggering CUDA_GRAPH disablement on NVGPUs even when batch-size
of 1 is used.
* Exclude `project_per_layer_input` by matching node names
This ensures that all other graphs which don't exhibit this pattern do
not have their behavior changed.
* Revert unnecessary formatting changes
* Minimal setup of webgpu backend with dawn. Just prints out the adapter and segfaults
* Initialize webgpu device
* Making progress on setting up the backend
* Finish more boilerplate/utility functions
* Organize file and work on alloc buffer
* Add webgpu_context to prepare for actually running some shaders
* Work on memset and add shader loading
* Work on memset polyfill
* Implement set_tensor as webgpu WriteBuffer, remove host_buffer stubs since webgpu doesn't support it
* Implement get_tensor and buffer_clear
* Finish rest of setup
* Start work on compute graph
* Basic mat mul working
* Work on emscripten build
* Basic WebGPU backend instructions
* Use EMSCRIPTEN flag
* Work on passing ci, implement 4d tensor multiplication
* Pass thread safety test
* Implement permuting for mul_mat and cpy
* minor cleanups
* Address feedback
* Remove division by type size in cpy op
* Fix formatting and add github action workflows for vulkan and metal (m-series) webgpu backends
* Fix name
* Fix macos dawn prefix path
Remove un-necessary templates from class definition and packing functions
Reduce deeply nested conditionals, if-else switching in mnapck function
Replace repetitive code with inline functions in Packing functions
2 ~ 7% improvement in Q8 Model
15 ~ 50% improvement in Q4 Model
Signed-off-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com>
* CUDA: add set rows for f32 and f16
* Review: change kernel params, use strides from host
* Use 1-d kernel
* Review: use int64_t for blockDim.x, rename nb->s for clarity
* fix 404 link
* update link in whisper.wasm example
* update example in command.wasm
* update link in bench.wasm example
* update link in stream.wasm example
