 Radoslav Gerganov
|
898acba681
rpc : add support for multiple devices (#16276)
|
4 mēneši atpakaļ |
 Jeff Bolz
|
c0b45097c3
rename optimize_graph to graph_optimize (#16082)
|
4 mēneši atpakaļ |
 Diego Devesa
|
360d6533db
ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type (#15797)
|
4 mēneši atpakaļ |
|
Jeff Bolz
|
e68aa10d8f
vulkan: sort graph to allow more parallel execution (#15850)
|
4 mēneši atpakaļ |
 William Tambellini
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
11 mēneši atpakaļ |
|
Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
1 gadu atpakaļ |
|
Diego Devesa
|
3420909dff
ggml : automatic selection of best CPU backend (#10606)
|
1 gadu atpakaļ |
|
Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 gadu atpakaļ |
|
Diego Devesa
|
c5b0f4b5d9
llama : refactor model loader with backend registry (#10026)
|
1 gadu atpakaļ |
|
Diego Devesa
|
6374743747
ggml : add backend registry / device interfaces to BLAS backend (#9752)
|
1 gadu atpakaļ |
 bandoti
|
d6fe7abf04
ggml: unify backend logging mechanism (#9709)
|
1 gadu atpakaļ |
|
Diego Devesa
|
c83ad6d01e
ggml-backend : add device and backend reg interfaces (#9707)
|
1 gadu atpakaļ |
 Johannes Gäßler
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 gadu atpakaļ |
 Georgi Gerganov
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 gadu atpakaļ |
