 Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
hai 1 ano |
 Gilad S.
|
43041d2eb3
ggml: load all backends from a user-provided search path (#10699)
|
hai 1 ano |
 Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
hai 1 ano |
 Johannes Gäßler
|
8a43e940ab
ggml: new optimization interface (ggml/988)
|
hai 1 ano |
|
Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
hai 1 ano |
|
Diego Devesa
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
hai 1 ano |
|
Diego Devesa
|
c5b0f4b5d9
llama : refactor model loader with backend registry (#10026)
|
hai 1 ano |
|
Diego Devesa
|
6374743747
ggml : add backend registry / device interfaces to BLAS backend (#9752)
|
hai 1 ano |
 Georgi Gerganov
|
d5ac8cf2f2
ggml : add metal backend registry / device (#9713)
|
hai 1 ano |
|
Johannes Gäßler
|
eee39bdc96
ggml: refactor cross entropy loss CPU impl. (ggml/976)
|
hai 1 ano |
 bandoti
|
d6fe7abf04
ggml: unify backend logging mechanism (#9709)
|
hai 1 ano |
|
Diego Devesa
|
c83ad6d01e
ggml-backend : add device and backend reg interfaces (#9707)
|
hai 1 ano |
|
Johannes Gäßler
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
hai 1 ano |
 Faisal Zaghloul
|
42c76d1358
Threadpool: take 2 (#8672)
|
hai 1 ano |
|
Georgi Gerganov
|
231cff5f6f
sync : ggml
|
hai 1 ano |
|
Johannes Gäßler
|
a15ef8f8a0
CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)
|
hai 1 ano |
|
Georgi Gerganov
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
hai 1 ano |
