 hipudding
|
204f2cf168
CANN: Add ggml_set_rows (#14943)
|
5 months ago |
 Sigbjørn Skjæret
|
138b288b59
cuda : add softcap fusion (#14907)
|
5 months ago |
 Johannes Gäßler
|
bbd0f91779
server-bench: make seed choice configurable (#14929)
|
5 months ago |
 Aman Gupta
|
0a5036bee9
CUDA: add roll (#14919)
|
5 months ago |
 lhez
|
8ad7b3e65b
opencl : add ops docs (#14910)
|
5 months ago |
 Leonard Mosescu
|
bda62193b2
test-backend-ops : extend test case filtering (#14865)
|
5 months ago |
 Radoslav Gerganov
|
c556418b60
llama-bench : use local GPUs along with RPC servers (#14917)
|
5 months ago |
 xctan
|
db16e2831c
ggml-cpu : deduplicate scalar implementations (#14897)
|
5 months ago |
 Akarshan Biswas
|
cd1fce6d4f
SYCL: Add set_rows support for quantized types (#14883)
|
5 months ago |
 Xuan-Son Nguyen
|
00fa15fedc
mtmd : add support for Voxtral (#14862)
|
5 months ago |
|
Johannes Gäßler
|
946b1f6859
CUDA: fix pointer incrementation in FA (#14916)
|
5 months ago |
 Dongliang Wei
|
6c6e397aff
model : add support for SmallThinker series (#14898)
|
5 months ago |
 Alberto Cabrera Pérez
|
afc0e89698
sycl: refactor quantization to q8_1 (#14815)
|
5 months ago |
 Georgi Gerganov
|
a5771c9eea
ops : update BLAS (#14914)
|
5 months ago |
|
Georgi Gerganov
|
c35f9eaf09
ops : update Metal (#14912)
|
5 months ago |
|
Georgi Gerganov
|
1f45f2890e
sync : ggml
|
5 months ago |
 Kai Pastor
|
613c5095c3
cmake : Indent ggml-config.cmake (ggml/1310)
|
6 months ago |
 Ed Addario
|
7f97599581
quantize : update README.md (#14905)
|
5 months ago |
 Ruben Ortlam
|
bf78f5439e
vulkan: add ops docs (#14900)
|
5 months ago |
|
Akarshan Biswas
|
bbfc849274
SYCL: add ops doc (#14901)
|
5 months ago |
 Daniel Bevenius
|
ca0ef2dddb
llama : clarify comment about pp and tg graphs [no ci] (#14895)
|
5 months ago |
 Erik Scholz
|
89d1029559
vulkan : add fp16 support for the conv_2d kernel (#14872)
|
5 months ago |
 Jeff Bolz
|
f1a4e72de5
vulkan: skip empty set_rows to avoid invalid API usage (#14860)
|
5 months ago |
 Gabriel Larson
|
4762ad7316
model : make rope_yarn_log_mul optional for deepseek2 (#14896)
|
5 months ago |
 Shunta Saito
|
1dc9614e06
llama : fix kq_scale for the attention layers of PLaMo2 (#14892)
|
5 months ago |
|
Aman Gupta
|
446595b9b3
Docs: add instructions for adding backends (#14889)
|
5 months ago |
 deepsek
|
66906cd82a
HIP: Enable Matrix cores for MMQ Kernels, Enable stream-K for CDNA 3 (#14624)
|
5 months ago |
|
hipudding
|
11dd5a44eb
CANN: Implement GLU ops (#14884)
|
5 months ago |
 R0CKSTAR
|
9b8f3c6c77
musa: fix build warnings (unused variable) (#14869)
|
5 months ago |
 Aaron Teo
|
c7f3169cd5
ggml-cpu : disable GGML_NNPA by default due to instability (#14880)
|
6 months ago |
