 Georgi Gerganov
|
374fe09cdd
ggml : use std::sort in ggml_argsort CPU implementation (#17211)
|
2 ماه پیش |
 duduta
|
73460f6278
ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 (#16805)
|
2 ماه پیش |
 Max Krasnyansky
|
395e286bc9
cpu: skip NOPs to avoid barriers (#17133)
|
2 ماه پیش |
|
Georgi Gerganov
|
852ce5180a
ggml : fix conv2d_dw SVE path (ggml/1380)
|
2 ماه پیش |
 Acly
|
cc98f8d349
ggml-cpu : bicubic interpolation (#16891)
|
2 ماه پیش |
 JJJYmmm
|
d261223d24
model: add support for qwen3vl series (#16780)
|
2 ماه پیش |
|
Max Krasnyansky
|
dcca0d3ab8
cpu: introduce chunking for flash attention (#16829)
|
2 ماه پیش |
|
Acly
|
10640e31aa
ggml : fix interpolate with align-corners and ne=1 (#16700)
|
2 ماه پیش |
 safranowith
|
466c1911ab
cpu : add FLOOR, CEIL, ROUND and TRUNC unary operators (#16083)
|
3 ماه پیش |
|
duduta
|
1deee0f8d4
cpu : optimize the ggml NORM operation (#15953)
|
3 ماه پیش |
|
Georgi Gerganov
|
1d6092fc72
tests : add -INF blocks to the KQ mask in the FA tests (#16380)
|
3 ماه پیش |
 Piotr Wilkin (ilintar)
|
34fcc5a4ac
model : Apertus model implementation (#15852)
|
3 ماه پیش |
 Sigbjørn Skjæret
|
3ecb2f671a
ggml : implement set_rows with i32 index (#16159)
|
4 ماه پیش |
 Xuan-Son Nguyen
|
0dd58b6877
ggml : refactor forward_dup for cpu backend (#16062)
|
4 ماه پیش |
 Daniel Bevenius
|
3913f8730e
ggml : fix padding in timestep embedding kernels (#15932)
|
4 ماه پیش |
|
Daniel Bevenius
|
9de447d94e
ggml-cpu : fix padding in ggml_timestep_embedding (#15917)
|
4 ماه پیش |
|
Xuan-Son Nguyen
|
9fcb29f22f
ggml: allow casting between f32 and i32 (#15783)
|
4 ماه پیش |
 leejet
|
0a1b3982cd
ggml: add ops for WAN video model (cuda && cpu) (#15669)
|
4 ماه پیش |
 compilade
|
73804145ab
ggml : fix SSM_SCAN for n_groups > 1 (#15625)
|
4 ماه پیش |
 xctan
|
1cf123a343
ggml-cpu : add basic RVV support for vector f32 ops (#15057)
|
4 ماه پیش |
 rmatif
|
92f7f0a53c
ggml: add `conv3d` op (#15182)
|
5 ماه پیش |
 Jonathan Graehl
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
5 ماه پیش |
|
Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 ماه پیش |
|
Georgi Gerganov
|
64978340b0
ggml : add asserts (#14720)
|
6 ماه پیش |
|
Xuan-Son Nguyen
|
98bab638fb
ggml : add ggml_scale_bias (#14417)
|
6 ماه پیش |
|
Sigbjørn Skjæret
|
28657a8229
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445)
|
6 ماه پیش |
|
Georgi Gerganov
|
9067487c44
ggml : fix FA mask dim 2 and 3 (#14505)
|
6 ماه پیش |
|
compilade
|
5d46babdc2
llama : initial Mamba-2 support (#9126)
|
6 ماه پیش |
|
Georgi Gerganov
|
ec68e84c32
ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435)
|
6 ماه پیش |
|
Acly
|
431b2c24f3
ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)
|
6 ماه پیش |
