Daniel Bevenius
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
4 miesięcy temu |
R0CKSTAR
|
8ad038c0fd
musa: add GGML_UNUSED_VARS (#15446)
|
4 miesięcy temu |
Diego Devesa
|
5682a3745f
sched : copy only the used experts when offloading prompt processing (#15346)
|
4 miesięcy temu |
teo
|
1bc664a26a
server: fix OpenAI API compatibility for usage statistics in chat streams (#15444)
|
4 miesięcy temu |
Johannes Gäßler
|
13aeb7aef2
CUDA: refactor FA support/selection code (#15454)
|
4 miesięcy temu |
Johannes Gäßler
|
7a6e91ad26
CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433)
|
4 miesięcy temu |
Jeff Bolz
|
fec9519802
vulkan: shorten pipeline name strings (#15431)
|
4 miesięcy temu |
Daniel Bevenius
|
657b8a77bd
chat: handle gpt-oss return/end token inconsistency (#15421)
|
4 miesięcy temu |
Jie Fu (傅杰)
|
ec5ab1a36c
common : fix context shift help message (#15448)
|
4 miesięcy temu |
xiaobing318
|
1a99c2d948
cmake : fix target include directories (#15450)
|
4 miesięcy temu |
Daniel Bevenius
|
37f10f955f
make : remove make in favor of CMake (#15449)
|
4 miesięcy temu |
Georgi Gerganov
|
2f37014073
lookahead : add sample command to readme (#15447)
|
4 miesięcy temu |
R0CKSTAR
|
a094f38143
musa: fix build warnings (#15258)
|
5 miesięcy temu |
lhez
|
fb22dd07a6
opencl: mark `argsort` unsupported if cols exceed workgroup limit (#15375)
|
5 miesięcy temu |
Georgi Gerganov
|
9ef6b0b835
model : add gpt-oss type strings (#15424)
|
5 miesięcy temu |
Gian-Carlo Pascutto
|
1e19f5d462
common : Add top-nsigma sampler to help globally (#15428)
|
5 miesięcy temu |
Georgi Gerganov
|
d2fcd91cf9
server : disable context shift by default (#15416)
|
5 miesięcy temu |
SHUAI YANG
|
a6d3cfe7fa
CANN: optimize rope operator (#15335)
|
5 miesięcy temu |
R0CKSTAR
|
67f09a3a27
musa: handle __hgt2_mask, available starting from MUSA SDK rc4.3.0 (#15413)
|
5 miesięcy temu |
Marvin Gießing
|
6424594c56
ggml-cpu: add mxfp4 VSX intrinsics for Power9+ (ppc64le) hardware (#15385)
|
5 miesięcy temu |
Xuan-Son Nguyen
|
e9288e8869
chat : clarify the meaning of reasoning_format (#15408)
|
5 miesięcy temu |
Georgi Gerganov
|
9d262f4bad
server : remove swa_full warning (#15399)
|
5 miesięcy temu |
Georgi Gerganov
|
f0d3c7405c
batched-bench : use rand tokens (#15398)
|
5 miesięcy temu |
Xuan-Son Nguyen
|
f08c4c0d8d
mtmd : clean up clip_n_output_tokens (#15391)
|
5 miesięcy temu |
Georgi Gerganov
|
6d7f1117e3
codeowners : remove mmv.*
|
5 miesięcy temu |
Georgi Gerganov
|
60212f1ead
sync : ggml
|
5 miesięcy temu |
Georgi Gerganov
|
f0c541d315
scripts : update sync scripts
|
5 miesięcy temu |
Sigbjørn Skjæret
|
baa9255a45
llama : merge conts and reshapes and remove unnecessary cont (#15380)
|
5 miesięcy temu |
Georgi Gerganov
|
3007baf201
readme : update hot topics (#15397)
|
5 miesięcy temu |
davidef
|
d1d8241600
server : fix incoming tasks not process in order (#15395)
|
5 miesięcy temu |