 Kai Pastor
|
73a8e5ca03
vulkan : fix 32-bit builds (ggml/1313)
|
5 meses atrás |
 Johannes Gäßler
|
92b8810ec7
CUDA: skip masked KV slices for all FA kernels (#14924)
|
5 meses atrás |
 Georgi Gerganov
|
00131d6eaf
tests : update for LLAMA_SET_ROWS=1 (#14961)
|
5 meses atrás |
|
Georgi Gerganov
|
1e15bfd42c
graph : fix stack-use-after-return (#14960)
|
5 meses atrás |
 Douglas Hanley
|
a118d80233
embeddings: fix extraction of CLS pooling results (#14927)
|
5 meses atrás |
 Xinpeng Dou
|
61550f8231
CANN: update ops docs (#14935)
|
5 meses atrás |
 uvos
|
aa79524c51
HIP: remove the use of __HIP_PLATFORM_AMD__, explicitly support only AMD targets (#14945)
|
5 meses atrás |
|
uvos
|
b77d11179d
HIP: add GGML_HIP_MMQ_MFMA option to allow disableing the MFMA path. (#14930)
|
5 meses atrás |
|
uvos
|
c7aa1364fd
HIP: Ignore unsupported unroll transformation in fattn-vec (#14931)
|
5 meses atrás |
 kallewoof
|
1a67fcc306
common : avoid logging partial messages (which can contain broken UTF-8 sequences) (#14937)
|
5 meses atrás |
 hipudding
|
204f2cf168
CANN: Add ggml_set_rows (#14943)
|
5 meses atrás |
 Sigbjørn Skjæret
|
138b288b59
cuda : add softcap fusion (#14907)
|
5 meses atrás |
|
Johannes Gäßler
|
bbd0f91779
server-bench: make seed choice configurable (#14929)
|
5 meses atrás |
 Aman Gupta
|
0a5036bee9
CUDA: add roll (#14919)
|
5 meses atrás |
 lhez
|
8ad7b3e65b
opencl : add ops docs (#14910)
|
5 meses atrás |
 Leonard Mosescu
|
bda62193b2
test-backend-ops : extend test case filtering (#14865)
|
5 meses atrás |
 Radoslav Gerganov
|
c556418b60
llama-bench : use local GPUs along with RPC servers (#14917)
|
5 meses atrás |
 xctan
|
db16e2831c
ggml-cpu : deduplicate scalar implementations (#14897)
|
5 meses atrás |
 Akarshan Biswas
|
cd1fce6d4f
SYCL: Add set_rows support for quantized types (#14883)
|
5 meses atrás |
 Xuan-Son Nguyen
|
00fa15fedc
mtmd : add support for Voxtral (#14862)
|
5 meses atrás |
|
Johannes Gäßler
|
946b1f6859
CUDA: fix pointer incrementation in FA (#14916)
|
5 meses atrás |
 Dongliang Wei
|
6c6e397aff
model : add support for SmallThinker series (#14898)
|
5 meses atrás |
 Alberto Cabrera Pérez
|
afc0e89698
sycl: refactor quantization to q8_1 (#14815)
|
5 meses atrás |
|
Georgi Gerganov
|
a5771c9eea
ops : update BLAS (#14914)
|
5 meses atrás |
|
Georgi Gerganov
|
c35f9eaf09
ops : update Metal (#14912)
|
5 meses atrás |
|
Georgi Gerganov
|
1f45f2890e
sync : ggml
|
5 meses atrás |
|
Kai Pastor
|
613c5095c3
cmake : Indent ggml-config.cmake (ggml/1310)
|
5 meses atrás |
 Ed Addario
|
7f97599581
quantize : update README.md (#14905)
|
5 meses atrás |
 Ruben Ortlam
|
bf78f5439e
vulkan: add ops docs (#14900)
|
5 meses atrás |
|
Akarshan Biswas
|
bbfc849274
SYCL: add ops doc (#14901)
|
5 meses atrás |
