 HimariO
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 anno fa |
 Djip007
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 anno fa |
 Xuan Son Nguyen
|
91c36c269b
server : (web ui) Various improvements, now use vite as bundler (#10599)
|
1 anno fa |
 Georgi Gerganov
|
8648c52101
make : deprecate (#10514)
|
1 anno fa |
 Wang Qin
|
43957ef203
build: update Makefile comments for C++ version change (#10598)
|
1 anno fa |
 Diego Devesa
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
1 anno fa |
 Tristan Druyen
|
be0e350c8b
Fix HIP flag inconsistency & build docs (#10524)
|
1 anno fa |
 R0CKSTAR
|
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
|
1 anno fa |
 Eric Curtin
|
0cc63754b8
Introduce llama-run (#10291)
|
1 anno fa |
|
Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 anno fa |
|
Georgi Gerganov
|
d9d54e498d
speculative : refactor and add a simpler example (#10362)
|
1 anno fa |
 Anthony Van de Gejuchte
|
3952a221af
Fix missing file renames in Makefile due to changes in commit ae8de6d50a (#10413)
|
1 anno fa |
|
Georgi Gerganov
|
cf32a9b93a
metal : refactor kernel args into structs (#10238)
|
1 anno fa |
 Johannes Gäßler
|
c3ea58aca4
CUDA: remove DMMV, consolidate F16 mult mat vec (#10318)
|
1 anno fa |
|
Georgi Gerganov
|
a4200cafad
make : add ggml-opt (#0)
|
1 anno fa |
|
Georgi Gerganov
|
84274a10c3
tests : remove test-grad0
|
1 anno fa |
|
Georgi Gerganov
|
8ee0d09ae6
make : auto-determine dependencies (#0)
|
1 anno fa |
|
slaren
|
883d206fbd
ggml : fix some build issues
|
1 anno fa |
 Charles Xu
|
1607a5e5b0
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921)
|
1 anno fa |
|
Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 anno fa |
|
Georgi Gerganov
|
ec450d3bbf
metal : opt-in compile flag for BF16 (#10218)
|
1 anno fa |
|
Xuan Son Nguyen
|
a71d81cf8c
server : revamp chat UI with vuejs and daisyui (#10175)
|
1 anno fa |
|
Diego Devesa
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
1 anno fa |
|
Diego Devesa
|
a6744e43e8
llama : add simple-chat example (#10124)
|
1 anno fa |
 Ma Mingfei
|
60ce97c9d8
add amx kernel for gemm (#8998)
|
1 anno fa |
|
Diego Devesa
|
c83ad6d01e
ggml-backend : add device and backend reg interfaces (#9707)
|
1 anno fa |
|
Georgi Gerganov
|
148844fe97
examples : remove benchmark (#9704)
|
1 anno fa |
|
R0CKSTAR
|
c35e586ea5
musa: enable building fat binaries, enable unified memory, and disable Flash Attention on QY1 (MTT S80) (#9526)
|
1 anno fa |
|
Georgi Gerganov
|
19514d632e
cmake : do not hide GGML options + rename option (#9465)
|
1 anno fa |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
1 anno fa |
