 Georgi Gerganov
|
d48ccf3ad4
sync : ggml (#6351)
|
hai 1 ano |
 hxer7963
|
069574775c
[Model] Add support for xverse (#6301)
|
hai 1 ano |
|
Georgi Gerganov
|
cfde806eb9
ci : fix BGE wget (#6383)
|
hai 1 ano |
 zhouwg
|
b910287954
readme : add project (#6356)
|
hai 1 ano |
 Matt Clayton
|
8093987090
cmake : add explicit metal version options (#6370)
|
hai 1 ano |
 Daniel Bevenius
|
057400a3fd
llama : remove redundant reshape in build_kv_store (#6369)
|
hai 1 ano |
 Pedro Cuenca
|
b75c38166c
convert : allow conversion of Mistral HF models (#6144)
|
hai 1 ano |
|
Georgi Gerganov
|
bfe7dafc9c
readme : add notice for UI list
|
hai 1 ano |
 Ouadie EL FAROUKI
|
5106ef482c
[SYCL] Revisited & updated SYCL build documentation (#6141)
|
hai 1 ano |
 Jared Van Bortel
|
be55134a53
convert : refactor vocab selection logic (#6355)
|
hai 1 ano |
 Ziang Wu
|
66ba560256
llava : fix MobileVLM (#6364)
|
hai 1 ano |
 compilade
|
0308f5e3d7
llama : fix command-r inference when omitting outputs (#6367)
|
hai 1 ano |
 Pierrick Hymbert
|
28cb9a09c4
ci: bench: fix master not schedule, fix commit status failed on external repo (#6365)
|
hai 1 ano |
 Ting Sun
|
cfc4d75df6
doc: fix outdated default value of batch size (#6336)
|
hai 1 ano |
 Eric Zhang
|
6902cb7f2e
server : stop gracefully on SIGTERM (#6348)
|
hai 1 ano |
 hutli
|
d2d8f38996
nix: removed unnessesary indentation
|
hai 1 ano |
|
hutli
|
d39b308eaf
nix: moved blas availability check to package inputs so it is still overridable
|
hai 1 ano |
|
hutli
|
c873976649
using blas.meta.available to check host platform
|
hai 1 ano |
 hutli
|
dbb03e2b9c
only using explicit blas if hostPlatform is allowed
|
hai 1 ano |
 Someone Serge
|
e9f17dc3bf
nix: .#windows: proper cross-compilation set-up
|
hai 1 ano |
|
Someone Serge
|
22a462cc1f
nix: package: don't introduce the dependency on python
|
hai 1 ano |
|
hutli
|
f6a0f5c642
nix: .#widnows: init
|
hai 1 ano |
|
Ziang Wu
|
d0e2f6416b
doc: fix typo in MobileVLM-README.md (#6181)
|
hai 1 ano |
 Neo Zhang Jianyu
|
25f4a613c4
[SYCL] fix set main gpu crash (#6339)
|
hai 1 ano |
|
Pierrick Hymbert
|
a016026a3a
server: continuous performance monitoring and PR comment (#6283)
|
hai 1 ano |
|
Someone Serge
|
53c7ec53d5
nix: ci: dont test cuda and rocm (for now)
|
hai 1 ano |
 slaren
|
e5b89a441a
ggml : fix bounds checking of zero size views (#6347)
|
hai 1 ano |
|
Georgi Gerganov
|
3a0345970e
make : whitespace
|
hai 1 ano |
 howlger
|
1e13987fba
embedding : show full embedding for single prompt (#6342)
|
hai 1 ano |
 AidanBeltonS
|
e82f9e2b83
[SYCL] Fix batched impl for NVidia GPU (#6164)
|
hai 1 ano |
