whisper.cpp/ggml
Alexey Kopytko b0c9f90059 SYCL: improve MoE prefill throughput (llama/23142)
- change `k_copy_src1_to_contiguous` so that uses a precomputed contiguous mapping where all rows "owned" by an expert are in one slice with a know starts and ends
- switch the `O(n_as * n_routed_rows)` contraption to a counting sort-based procedure with `O(n_as + n_routed_rows)` complexity
2026-05-25 12:26:07 +03:00
..
cmake cmake : add FindNCCL.cmake (ggml/0) 2026-05-02 15:02:42 +03:00
include ggml.h: correct ggml_silu_back arg docstring (a=dy, b=x) (ggml/1500) 2026-05-25 12:26:07 +03:00
src SYCL: improve MoE prefill throughput (llama/23142) 2026-05-25 12:26:07 +03:00
.gitignore whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
CMakeLists.txt ggml : bump version to 0.12.0 (ggml/1494) 2026-05-25 12:26:07 +03:00