 Xuan-Son Nguyen
|
98bab638fb
ggml : add ggml_scale_bias (#14417)
|
há 7 meses atrás |
 Sigbjørn Skjæret
|
28657a8229
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445)
|
há 7 meses atrás |
 Johannes Gäßler
|
c8c4495b8d
ggml: backward pass for split swiglu (#14483)
|
há 7 meses atrás |
 Georgi Gerganov
|
9067487c44
ggml : fix FA mask dim 2 and 3 (#14505)
|
há 7 meses atrás |
 compilade
|
5d46babdc2
llama : initial Mamba-2 support (#9126)
|
há 7 meses atrás |
 Daniel Bevenius
|
c46944aa25
ggml : add version function to get lib version (ggml/1286)
|
há 7 meses atrás |
|
Georgi Gerganov
|
ec68e84c32
ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435)
|
há 7 meses atrás |
 Björn Ganster
|
68b3cd6514
ggml : Callback before abort (#14481)
|
há 7 meses atrás |
|
Georgi Gerganov
|
a6a47958a1
ggml : remove trailing whitespace (#0)
|
há 7 meses atrás |
 Acly
|
431b2c24f3
ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)
|
há 7 meses atrás |
 Aman Gupta
|
0a5a3b5cdf
Add Conv2d for CPU (#14388)
|
há 7 meses atrás |
|
Sigbjørn Skjæret
|
a0535ffa0d
ggml : implement REGLU/GEGLU/SWIGLU ops (#14158)
|
há 7 meses atrás |
 Jeff Bolz
|
bd9c981d72
vulkan: Add fusion support for RMS_NORM+MUL (#14366)
|
há 7 meses atrás |
 Radoslav Gerganov
|
8d94219a4a
ggml : add ggml_set_rows (#14274)
|
há 7 meses atrás |
 Aaron Teo
|
60ef23d6c1
ggml-cpu: enable IBM NNPA Vector Intrinsics (#14317)
|
há 7 meses atrás |
|
Acly
|
b7147673f2
Add `ggml_roll` (ggml/1274)
|
há 7 meses atrás |
|
Daniel Bevenius
|
bbe98d2784
ggml : remove unused ggml_context_container (ggml/1272)
|
há 7 meses atrás |
|
Georgi Gerganov
|
a7b8d35f78
sync : whisper.cpp (ggml/1250)
|
há 8 meses atrás |
 Daniel Tang
|
fedf034a98
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
há 8 meses atrás |
|
Xuan-Son Nguyen
|
a8ea03d8ad
ggml : add ggml_repeat_4d (#13824)
|
há 8 meses atrás |
|
Xuan-Son Nguyen
|
cf4cb59e64
ggml : add ggml_gelu_erf() (#13667)
|
há 8 meses atrás |
 Diego Devesa
|
8b5e19aea6
ggml : fix apple OS check in ggml_print_backtrace (ggml/1229)
|
há 8 meses atrás |
|
Daniel Tang
|
60aea028b5
ggml : Fix missing backtrace on Linux (ggml/1228)
|
há 8 meses atrás |
|
Johannes Gäßler
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
há 9 meses atrás |
|
Georgi Gerganov
|
611aa914ef
metal : optimize MoE for large batches (#13388)
|
há 9 meses atrás |
|
Johannes Gäßler
|
2356fb1d53
CUDA: fix bad asserts for partial offload (#13337)
|
há 9 meses atrás |
 SXX
|
77d5e9a76a
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107)
|
há 9 meses atrás |
|
Georgi Gerganov
|
87616f0680
ggml : fix trailing whitespaces (#0)
|
há 9 meses atrás |
|
Acly
|
c6e8cc28c1
ggml : Depthwise 2D convolution (ggml/1152)
|
há 9 meses atrás |
|
Diego Devesa
|
fe92821ea9
ggml : add bilinear upscale support (ggml/1185)
|
há 10 meses atrás |
