 Marcus Dunn
|
af4980bfed
readme : add link to rust bindings (#5148)
|
%!s(int64=2) %!d(string=hai) anos |
 sharpHL
|
f2e69d28c0
llama : add support for Orion-14B (#5118)
|
%!s(int64=2) %!d(string=hai) anos |
 Kyle Mistele
|
39baaf55a1
docker : add server-first container images (#5157)
|
%!s(int64=2) %!d(string=hai) anos |
 John
|
6db2b41a76
llava : support for Yi-VL and fix for mobileVLM (#5093)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
753eafed0e
sync : ggml
|
%!s(int64=2) %!d(string=hai) anos |
 Judd
|
e976423005
ggml : check ggml_add src1 type (ggml/708)
|
%!s(int64=2) %!d(string=hai) anos |
 Michael Klimenko
|
35a2ee9143
Remove unused data and add fixes (#5154)
|
%!s(int64=2) %!d(string=hai) anos |
 Maximilian Winter
|
ec903c0341
server : add self-extend support (#5104)
|
%!s(int64=2) %!d(string=hai) anos |
 0cc4m
|
a1d6df129b
Add OpenCL add kernel (#5151)
|
%!s(int64=2) %!d(string=hai) anos |
 Jared Van Bortel
|
bbe7c56c99
cmake : pass CPU architecture flags to nvcc (#5146)
|
%!s(int64=2) %!d(string=hai) anos |
 slaren
|
62fead3ea0
cuda : fix tensor size calculation for non-split buffer (#5145)
|
%!s(int64=2) %!d(string=hai) anos |
|
slaren
|
15b4538ff2
ggml-alloc : add 10% margin to the buffer sizes (#5149)
|
%!s(int64=2) %!d(string=hai) anos |
 snadampal
|
7032f4f634
ggml : update softmax n_task calculation (#5126)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
5f1925a8ce
scripts : move run-with-preset.py from root to scripts folder
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
3b7c914de2
tests : gitignore test-c.o
|
%!s(int64=2) %!d(string=hai) anos |
 Xuan Son Nguyen
|
48c857aa10
server : refactored the task processing logic (#5065)
|
%!s(int64=2) %!d(string=hai) anos |
 crasm
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
%!s(int64=2) %!d(string=hai) anos |
 Paul Tsochantaris
|
6dd3c28c9c
metal : remove unused `n_buffers` and `buffers` (#5129)
|
%!s(int64=2) %!d(string=hai) anos |
 Riceball LEE
|
38b431de23
gguf : fix "general.alignment" type in gguf_reader.py (#5136)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
aad0b01d73
readme : update hot topics
|
%!s(int64=2) %!d(string=hai) anos |
 Kawrakow
|
1182cf4d4f
Another bucket sort (#5109)
|
%!s(int64=2) %!d(string=hai) anos |
 XiaotaoChen
|
fe54033b69
readme : add MobileVLM 1.7B/3B to the supported models list (#5107)
|
%!s(int64=2) %!d(string=hai) anos |
 l3utterfly
|
5eaf9964fc
llama : dynamic temperature sampling (#4972)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jared Van Bortel
|
d292f4f204
examples : make pydantic scripts pass mypy and support py3.8 (#5099)
|
%!s(int64=2) %!d(string=hai) anos |
 Valentin Konovalov
|
256d1bb0dd
android : use release cmake build type by default (#5123)
|
%!s(int64=2) %!d(string=hai) anos |
|
Kawrakow
|
faa3526a1e
Fix Q3_K_XS for MoE models (#5113)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
ddc5a5033f
metal : show compile log messages
|
%!s(int64=2) %!d(string=hai) anos |
 Engininja2
|
cd4fddb29f
cuda : fix 2-bit quants on amd hip (#5105)
|
%!s(int64=2) %!d(string=hai) anos |
 Michael Hueschen
|
c9b316c78f
nix-shell: use addToSearchPath
|
%!s(int64=2) %!d(string=hai) anos |
|
Michael Hueschen
|
bf63d695b8
nix: add cc to devShell LD_LIBRARY_PATH
|
%!s(int64=2) %!d(string=hai) anos |
