 Eve
|
f7b1116af1
update release requirements (#11897)
|
il y a 11 mois |
 Georgi Gerganov
|
68ff663a04
repo : update links to new url (#11886)
|
il y a 11 mois |
 Rémy O
|
fc1b0d0936
vulkan: initial support for IQ1_S and IQ1_M quantizations (#11528)
|
il y a 11 mois |
|
Eve
|
a4f011e8d0
vulkan: linux builds + small subgroup size fixes (#11767)
|
il y a 11 mois |
 R0CKSTAR
|
bd6e55bfd3
musa: bump MUSA SDK version to rc3.1.1 (#11822)
|
il y a 11 mois |
 Jeff Bolz
|
2c6c8df56d
vulkan: optimize coopmat2 iq2/iq3 callbacks (#11521)
|
il y a 11 mois |
 Michał Moskal
|
ff227703d6
sampling : support for llguidance grammars (#10224)
|
il y a 1 an |
 Olivier Chafik
|
53debe6f3c
ci: use sccache on windows HIP jobs (#11553)
|
il y a 1 an |
|
Olivier Chafik
|
5bbc7362cb
ci: simplify cmake build commands (#11548)
|
il y a 1 an |
|
Olivier Chafik
|
aa6fb13213
`ci`: use sccache on windows instead of ccache (#11545)
|
il y a 1 an |
|
Olivier Chafik
|
553f1e46e9
`ci`: ccache for all github worfklows (#11516)
|
il y a 1 an |
 Rémy Oudompheng
|
66ee4f297c
vulkan: implement initial support for IQ2 and IQ3 quantizations (#11360)
|
il y a 1 an |
 bandoti
|
19f65187cb
cmake: add ggml find package (#11369)
|
il y a 1 an |
|
Georgi Gerganov
|
00c24acb2a
ci : fix line breaks on windows builds (#11409)
|
il y a 1 an |
 jiahao su
|
466ea66f33
CANN: Add Ascend CANN build ci (#10217)
|
il y a 1 an |
|
Georgi Gerganov
|
9755129c27
release : pack /lib in the packages (#11392)
|
il y a 1 an |
 Eric Curtin
|
a1649cc13f
Adding linenoise.cpp to llama-run (#11252)
|
il y a 1 an |
|
Georgi Gerganov
|
4dd34ff831
cmake : add sanitizer flags for llama.cpp (#11279)
|
il y a 1 an |
 Xuan Son Nguyen
|
f7cd13301c
ci : use actions from ggml-org (#11140)
|
il y a 1 an |
|
Georgi Gerganov
|
0d52a69e4b
ci : fix cmake option (#11125)
|
il y a 1 an |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
il y a 1 an |
|
Eve
|
7b1ec53f56
vulkan: bugfixes for small subgroup size systems + llvmpipe test (#10809)
|
il y a 1 an |
 lhez
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
il y a 1 an |
 Diego Devesa
|
43ed389a3f
llama : use cmake for swift build (#10525)
|
il y a 1 an |
|
Georgi Gerganov
|
8648c52101
make : deprecate (#10514)
|
il y a 1 an |
|
Diego Devesa
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
il y a 1 an |
|
Diego Devesa
|
e90688edd0
ci : fix tag name in cuda and hip releases (#10566)
|
il y a 1 an |
|
Diego Devesa
|
46c69e0e75
ci : faster CUDA toolkit installation method and use ccache (#10537)
|
il y a 1 an |
|
Diego Devesa
|
c9b00a70b0
ci : fix cuda releases (#10532)
|
il y a 1 an |
 Neo Zhang Jianyu
|
0bbd2262a3
restore the condistion to build & update pacakge when merge (#10507)
|
il y a 1 an |
