 bandoti
|
f95caa7954
cmake: add link dependencies to cmake find pkg (#10433)
|
1 سال پیش |
 Diego Devesa
|
fab5d30ff6
llama : add .clang-format file (#10415)
|
1 سال پیش |
 Jeff Bolz
|
8fd4b7fa29
vulkan: copy iq4_nl LUT into shared memory (#10409)
|
1 سال پیش |
|
Jeff Bolz
|
1bacb9f625
vulkan: further optimize mul_mat_vec using larger loads (#10387)
|
1 سال پیش |
 Neo Zhang Jianyu
|
ad21c9e1f1
update rel to 4040 (#10395)
|
1 سال پیش |
 Anthony Van de Gejuchte
|
3952a221af
Fix missing file renames in Makefile due to changes in commit ae8de6d50a (#10413)
|
1 سال پیش |
 haopeng
|
42ae10bbcd
add cmake rvv support (#10411)
|
1 سال پیش |
 Georgi Gerganov
|
9fe0fb0626
sync : ggml
|
1 سال پیش |
 Plamen Minev
|
611fabd792
metal : fox offset integer overflows in im2col (ggml/1015)
|
1 سال پیش |
 PAB
|
12b0ad953a
metal : add `GGML_UNARY_OP_ELU` kernel (ggml/1018)
|
1 سال پیش |
 蕭澧邦
|
342397dc7e
cmake: force MSVC compiler charset to utf-8 (#9989)
|
1 سال پیش |
|
bandoti
|
2a11b6b094
Add required ggml-base and backend libs to cmake pkg (#10407)
|
1 سال پیش |
|
Diego Devesa
|
3ee6382d48
cuda : fix CUDA_FLAGS not being applied (#10403)
|
1 سال پیش |
|
Georgi Gerganov
|
8e752a777b
llama : add check for KV cache shifts (#10401)
|
1 سال پیش |
 Shane A
|
a88ad007de
llama : add OLMo November 2024 support (#10394)
|
1 سال پیش |
 Romain Biessy
|
2a1507c162
sycl : Add option to set the SYCL architecture for all targets (#10266)
|
1 سال پیش |
|
Jeff Bolz
|
b3e585988f
vulkan: Optimize soft_max (#10301)
|
1 سال پیش |
 Alberto Cabrera Pérez
|
557924f222
sycl: Revert MUL_MAT_OP support changes (#10385)
|
1 سال پیش |
|
Diego Devesa
|
d3481e6316
cuda : only use native when supported by cmake (#10389)
|
1 سال پیش |
|
bandoti
|
531cb1c233
Skip searching root path for cross-compile builds (#10383)
|
1 سال پیش |
|
Jeff Bolz
|
f139d2ea61
vulkan: remove use of null initializer (#10372)
|
1 سال پیش |
|
Georgi Gerganov
|
2eb76b2a5e
flake.lock: Update (#10346)
|
1 سال پیش |
 0cc4m
|
9b75f03cd2
Vulkan: Fix device info output format specifiers (#10366)
|
1 سال پیش |
 Johannes Gäßler
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
1 سال پیش |
|
Johannes Gäßler
|
76e9e58b78
CUDA: fix MMV kernel being used for FP16 src1 (#10357)
|
1 سال پیش |
|
Johannes Gäßler
|
ce2e59ba10
CMake: fix typo in comment [no ci] (#10360)
|
1 سال پیش |
|
Diego Devesa
|
be5caccef9
llama : only use default buffer types for the KV cache (#10358)
|
1 سال پیش |
|
Georgi Gerganov
|
20a780c7b6
gitignore : ignore local run scripts [no ci]
|
1 سال پیش |
|
Georgi Gerganov
|
cf32a9b93a
metal : refactor kernel args into structs (#10238)
|
1 سال پیش |
 FirstTimeEZ
|
a43178299c
ggml : fix undefined reference to 'getcpu' (#10354)
|
1 سال پیش |
