llama.cpp/ggml-cpu at 1e58ee1318429a3e97aa66f3034cdfd65ffc6c34 - llama.cpp - Gitea4PDT

RYDE-WORK/llama.cpp

mirror of https://github.com/RYDE-WORK/llama.cpp.git synced 2026-01-23 16:13:25 +08:00

History

Dan Johansson 1e58ee1318

ggml : optimize Q4_0 into Q4_0_X_Y repack (#10324 )

2024-11-16 01:53:37 +01:00

..

ggml : build backends as libraries (#10256 )

2024-11-14 18:04:35 +01:00

ggml : build backends as libraries (#10256 )

2024-11-14 18:04:35 +01:00

CMakeLists.txt

Make updates to fix issues with clang-cl builds while using AVX512 flags (#10314 )

2024-11-15 22:27:00 +01:00

ggml-cpu-aarch64.c

ggml : optimize Q4_0 into Q4_0_X_Y repack (#10324 )

2024-11-16 01:53:37 +01:00

ggml-cpu-aarch64.h

backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921 )

2024-11-15 01:28:50 +01:00

ggml-cpu-impl.h

ggml : build backends as libraries (#10256 )

2024-11-14 18:04:35 +01:00

ggml-cpu-quants.c

AVX BF16 and single scale quant optimizations (#10212 )

2024-11-15 12:47:58 +01:00

ggml-cpu-quants.h

ggml : build backends as libraries (#10256 )

2024-11-14 18:04:35 +01:00

ggml-cpu.c

AVX BF16 and single scale quant optimizations (#10212 )

2024-11-15 12:47:58 +01:00

ggml-cpu.cpp

backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921 )

2024-11-15 01:28:50 +01:00