6ab4e50d9c
ggml-cpu : add RISC-V Zvfh impl for ggml_vec_mad_f16 ( #17448 )
...
* ggml-cpu : add RISC-V Zvfh impl for ggml_vec_mad_f16
* ggml-cpu : dedup scalar impl
* Update ggml/src/ggml-cpu/vec.h
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-11-26 15:33:05 +02:00
xctan and GitHub
7f09a680af
ggml-cpu : optimize RVV q2_k and q3_k kernels ( #16887 )
2025-11-06 18:12:45 +02:00
xctan and GitHub
05c0380f2a
ggml-cpu : optimize RVV kernels ( #15720 )
...
* ggml-cpu : optimize rvv ggml_vec_dot_f32
* ggml-cpu : optimize 128-bit rvv ggml_vec_dot_q4_K_q8_K
* ggml-cpu : fix riscv arch flags
* ggml-cpu : add more rvv ops
* ggml-cpu : optimize rvv ggml_vec_dot_q4_K_q8_K
* ggml-cpu : optimize rvv ggml_vec_dot_q6_K_q8_K
* ggml-cpu : minor rvv adjustments
* ggml-cpu : fix riscv include
2025-09-03 16:16:21 +08:00
xctan and GitHub
1cf123a343
ggml-cpu : add basic RVV support for vector f32 ops ( #15057 )
...
* ggml-cpu : add basic RVV support for vector f32 ops
* ggml-cpu : add RVV support for f32 softmax
2025-08-27 16:44:22 +08:00
xctan and GitHub
db16e2831c
ggml-cpu : deduplicate scalar implementations ( #14897 )
...
* remove redundant code in riscv
* remove redundant code in arm
* remove redundant code in loongarch
* remove redundant code in ppc
* remove redundant code in s390
* remove redundant code in wasm
* remove redundant code in x86
* remove fallback headers
* fix x86 ggml_vec_dot_q8_0_q8_0
2025-07-28 17:40:24 +02:00
xctan and GitHub
860a9e4eef
ggml-cpu : remove the weak alias trick ( #14221 )
2025-06-17 12:58:32 +03:00
xctan and GitHub
3555b3004b
ggml-cpu : rework weak alias on apple targets ( #14146 )
...
* ggml-cpu : rework weak alias on apple targets
* fix powerpc detection
* fix ppc detection
* fix powerpc detection on darwin
2025-06-16 13:54:15 +08:00
xctan and GitHub
05f6ac6283
ggml : riscv: add xtheadvector support ( #13720 )
...
* ggml : riscv: add xtheadvector support
* ggml : clean up some macro usage
2025-05-27 16:21:36 +03:00
xctan and GitHub
24feaec057
ggml : riscv: add 128-bit RVV support ( #12530 )
...
* ggml : add 128-bit RVV support
* ggml : revert to old RVV 256+ q2_K, q3_K, q4_K, q6_K impl
* remove trailing whitespaces
* restructure vector length selection code
2025-03-27 08:38:34 +02:00
