 rmatif
|
92f7f0a53c
ggml: add `conv3d` op (#15182)
|
5 miesięcy temu |
 Jonathan Graehl
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
5 miesięcy temu |
 Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 miesięcy temu |
|
Georgi Gerganov
|
64978340b0
ggml : add asserts (#14720)
|
6 miesięcy temu |
 Xuan-Son Nguyen
|
98bab638fb
ggml : add ggml_scale_bias (#14417)
|
6 miesięcy temu |
 Sigbjørn Skjæret
|
28657a8229
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445)
|
6 miesięcy temu |
|
Georgi Gerganov
|
9067487c44
ggml : fix FA mask dim 2 and 3 (#14505)
|
6 miesięcy temu |
 compilade
|
5d46babdc2
llama : initial Mamba-2 support (#9126)
|
6 miesięcy temu |
|
Georgi Gerganov
|
ec68e84c32
ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435)
|
6 miesięcy temu |
 Acly
|
431b2c24f3
ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)
|
6 miesięcy temu |
 Aman Gupta
|
0a5a3b5cdf
Add Conv2d for CPU (#14388)
|
6 miesięcy temu |
|
Sigbjørn Skjæret
|
a0535ffa0d
ggml : implement REGLU/GEGLU/SWIGLU ops (#14158)
|
6 miesięcy temu |
 Radoslav Gerganov
|
8d94219a4a
ggml : add ggml_set_rows (#14274)
|
6 miesięcy temu |
 Aaron Teo
|
60ef23d6c1
ggml-cpu: enable IBM NNPA Vector Intrinsics (#14317)
|
6 miesięcy temu |
|
Acly
|
b7147673f2
Add `ggml_roll` (ggml/1274)
|
7 miesięcy temu |
 Diego Devesa
|
482548716f
releases : use dl backend for linux release, remove arm64 linux release (#13996)
|
7 miesięcy temu |
 Vineel Abhinav
|
dd8ba93416
ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (#13882)
|
7 miesięcy temu |
|
Vineel Abhinav
|
1b8fb8152d
ggml: aarch64: Implement SVE F32 kernels for vector functions (#13843)
|
7 miesięcy temu |
|
Xuan-Son Nguyen
|
cf4cb59e64
ggml : add ggml_gelu_erf() (#13667)
|
8 miesięcy temu |
 Daniel Bevenius
|
13b0a04597
whisper: remove MSVC warnings pragmas (whisper/3090)
|
8 miesięcy temu |
 SXX
|
77d5e9a76a
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107)
|
8 miesięcy temu |
|
Acly
|
c6e8cc28c1
ggml : Depthwise 2D convolution (ggml/1152)
|
9 miesięcy temu |
|
Diego Devesa
|
fe92821ea9
ggml : add bilinear upscale support (ggml/1185)
|
9 miesięcy temu |
|
Diego Devesa
|
459895c326
ggml : add more generic custom op, remove deprecated custom ops (ggml/1183)
|
9 miesięcy temu |
|
Georgi Gerganov
|
a19b5cef16
llama : fix FA when KV cache is not used (i.e. embeddings) (#12825)
|
9 miesięcy temu |
 cmdr2
|
995083e4ed
cpu: move all the operators into a separate c++ file (except mul_mat) (ggml/1167)
|
9 miesięcy temu |
