 Piotr Wilkin
|
344331c2b6
First draft
|
hai 4 meses |
 Georgi Gerganov
|
b0d52998b9
cuda : fix supports_op condition for get_rows when number of blocks is too large (#15868)
|
hai 4 meses |
 Xuan-Son Nguyen
|
9fcb29f22f
ggml: allow casting between f32 and i32 (#15783)
|
hai 4 meses |
 leejet
|
0a1b3982cd
ggml: add ops for WAN video model (cuda && cpu) (#15669)
|
hai 4 meses |
 rmatif
|
92f7f0a53c
ggml: add `conv3d` op (#15182)
|
hai 5 meses |
 R0CKSTAR
|
8ad038c0fd
musa: add GGML_UNUSED_VARS (#15446)
|
hai 5 meses |
 Jonathan Graehl
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
hai 5 meses |
 Judd
|
c24f4e2688
ggml : update `ggml_rope_multi` (#12665)
|
hai 5 meses |
|
Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
hai 5 meses |
|
Xuan-Son Nguyen
|
98bab638fb
ggml : add ggml_scale_bias (#14417)
|
hai 6 meses |
 Aman Gupta
|
75c91de6e9
CUDA: add bilinear interpolation for upscale (#14563)
|
hai 6 meses |
 Sigbjørn Skjæret
|
28657a8229
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445)
|
hai 7 meses |
|
Georgi Gerganov
|
9067487c44
ggml : fix FA mask dim 2 and 3 (#14505)
|
hai 7 meses |
 compilade
|
5d46babdc2
llama : initial Mamba-2 support (#9126)
|
hai 7 meses |
 Daniel Bevenius
|
c46944aa25
ggml : add version function to get lib version (ggml/1286)
|
hai 7 meses |
|
Georgi Gerganov
|
ec68e84c32
ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435)
|
hai 7 meses |
 Björn Ganster
|
68b3cd6514
ggml : Callback before abort (#14481)
|
hai 7 meses |
 Acly
|
431b2c24f3
ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)
|
hai 7 meses |
|
Aman Gupta
|
0a5a3b5cdf
Add Conv2d for CPU (#14388)
|
hai 7 meses |
|
Sigbjørn Skjæret
|
a0535ffa0d
ggml : implement REGLU/GEGLU/SWIGLU ops (#14158)
|
hai 7 meses |
 Radoslav Gerganov
|
8d94219a4a
ggml : add ggml_set_rows (#14274)
|
hai 7 meses |
|
Acly
|
b7147673f2
Add `ggml_roll` (ggml/1274)
|
hai 7 meses |
|
Radoslav Gerganov
|
af6f91db47
ggml : remove ggml_graph_import and ggml_graph_export declarations (ggml/1247)
|
hai 8 meses |
 Max Krasnyansky
|
053b1539c0
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (#12995)
|
hai 8 meses |
|
Xuan-Son Nguyen
|
a8ea03d8ad
ggml : add ggml_repeat_4d (#13824)
|
hai 8 meses |
|
Xuan-Son Nguyen
|
e16c4731c7
ggml : fix the order of ggml_unary_op (#13718)
|
hai 8 meses |
|
Xuan-Son Nguyen
|
cf4cb59e64
ggml : add ggml_gelu_erf() (#13667)
|
hai 8 meses |
 Johannes Gäßler
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
hai 8 meses |
|
Johannes Gäßler
|
2356fb1d53
CUDA: fix bad asserts for partial offload (#13337)
|
hai 8 meses |
|
Johannes Gäßler
|
69699be48a
CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (#13137)
|
hai 9 meses |
