Commit 03ec944
authored
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4&size=40){kind=avatar}
chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b8685) (#844)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>1 parent 073b542 commit 03ec944
1 file changed
Lines changed: 1 addition & 1 deletion
- common/console.cpp+5-4
- convert_hf_to_gguf.py+2-4
- docs/build.md+1-1
- docs/multimodal.md+1
- docs/ops.md+1-1
- docs/ops/WebGPU.csv+527-618
- ggml/include/ggml.h+3-1
- ggml/src/ggml-common.h+11
- ggml/src/ggml-cpu/arch-fallback.h+7
- ggml/src/ggml-cpu/arch/arm/quants.c+103
- ggml/src/ggml-cpu/arch/loongarch/quants.c-1
- ggml/src/ggml-cpu/arch/powerpc/quants.c-1
- ggml/src/ggml-cpu/arch/s390/quants.c-1
- ggml/src/ggml-cpu/arch/wasm/quants.c-1
- ggml/src/ggml-cpu/ggml-cpu.c+6
- ggml/src/ggml-cpu/ops.cpp+2
- ggml/src/ggml-cpu/quants.c+49
- ggml/src/ggml-cpu/quants.h+3
- ggml/src/ggml-cuda/fattn-common.cuh+153-25
- ggml/src/ggml-quants.c+75
- ggml/src/ggml-quants.h+3
- ggml/src/ggml-sycl/dequantize.hpp+16
- ggml/src/ggml-sycl/dmmv.cpp+103-1
- ggml/src/ggml-sycl/fattn-tile.hpp+10
- ggml/src/ggml-sycl/ggml-sycl.cpp+41-1
- ggml/src/ggml-sycl/mmvq.cpp+26-1
- ggml/src/ggml-sycl/quants.hpp+21
- ggml/src/ggml-sycl/vecdotq.hpp+40
- ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp+133-1
- ggml/src/ggml-webgpu/ggml-webgpu.cpp+202
- ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl+2
- ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_id.wgsl+193
- ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_id_gather.wgsl+55
- ggml/src/ggml.c+10
- gguf-py/gguf/constants.py+3
- include/llama.h+1
- scripts/compare-llama-bench.py+5-2
- src/llama-model-loader.cpp+2
- src/llama-quant.cpp+1
- src/llama-vocab.cpp+15-1
- tests/test-quantize-fns.cpp+5
- tools/llama-bench/README.md+2
- tools/llama-bench/llama-bench.cpp+100-4
- tools/mtmd/tests.sh+1
- tools/quantize/quantize.cpp+1
- tools/server/server-http.cpp+3-2
0 commit comments