 Xuan-Son Nguyen
|
9fcb29f22f
ggml: allow casting between f32 and i32 (#15783)
|
4 月之前 |
 Aaron Teo
|
186415d595
ggml-cpu: drop support for nnpa intrinsics (#15821)
|
4 月之前 |
 Radoslav Gerganov
|
8d94219a4a
ggml : add ggml_set_rows (#14274)
|
6 月之前 |
|
Aaron Teo
|
60ef23d6c1
ggml-cpu: enable IBM NNPA Vector Intrinsics (#14317)
|
6 月之前 |
 SXX
|
77d5e9a76a
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107)
|
8 月之前 |
 Rémy O
|
07d1572347
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (#12154)
|
10 月之前 |
 Aaron Teo
|
af7747c95a
ggml-cpu: Support s390x SIMD Instruction Set (#12019)
|
10 月之前 |
 Charles Xu
|
c5d91a7400
ggml-cpu: Add CPU backend support for KleidiAI library (#11390)
|
11 月之前 |
 Georgi Gerganov
|
68ff663a04
repo : update links to new url (#11886)
|
11 月之前 |
 Djip007
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 年之前 |
 Shupei Fan
|
c202cef168
ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)
|
1 年之前 |
 Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 年之前 |
|
Charles Xu
|
1607a5e5b0
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921)
|
1 年之前 |
|
Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 年之前 |
|
Diego Devesa
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
1 年之前 |
