 slaren
|
e7e4df031b
llama : ggml-backend integration (#4766)
|
il y a 2 ans |
 Georgi Gerganov
|
ba66175132
sync : ggml (fix im2col) (#4591)
|
il y a 2 ans |
|
slaren
|
d232aca5a7
llama : initial ggml-backend integration (#4520)
|
il y a 2 ans |
|
Georgi Gerganov
|
fe680e3d10
sync : ggml (new ops, tests, backend, etc.) (#4359)
|
il y a 2 ans |
|
Georgi Gerganov
|
ef47ec18da
ggml : add ggml_soft_max_ext (#4256)
|
il y a 2 ans |
|
Georgi Gerganov
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
il y a 2 ans |
|
slaren
|
875fb42871
ggml-alloc : fix backend assignments of views (#3982)
|
il y a 2 ans |
|
slaren
|
95bd60a0a6
ggml-alloc : fix assert in debug builds (#3555)
|
il y a 2 ans |
|
Georgi Gerganov
|
db3abcc114
sync : ggml (ggml-backend) (#3548)
|
il y a 2 ans |
 xaedes
|
0e76a8992c
train : finetune LORA (#2632)
|
il y a 2 ans |
|
Georgi Gerganov
|
8c00b7a6ff
sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192)
|
il y a 2 ans |
 Przemysław Pawełczyk
|
cb6c44c5e0
build : do not use _GNU_SOURCE gratuitously (#2035)
|
il y a 2 ans |
|
slaren
|
ebc96086af
ggml-alloc : correctly check mmap return value for errors (#3075)
|
il y a 2 ans |
 Cebtenzzre
|
00d62adb79
fix some warnings from gcc and clang-tidy (#3038)
|
il y a 2 ans |
|
slaren
|
cf9b08485c
ggml-alloc : use virtual memory for measurement (#2973)
|
il y a 2 ans |
 Jhen-Jie Hong
|
21f3d1be86
k-quants : fix build on armv7 (android only) (#2920)
|
il y a 2 ans |
|
slaren
|
06abf8eeba
ggml : add view_src and view_offs to ggml_tensor for views (#2874)
|
il y a 2 ans |
|
xaedes
|
44c117f41e
train : mem usage and other improvements (#2439)
|
il y a 2 ans |
|
Georgi Gerganov
|
35feac6560
ggml : sync (mem align to header + conv_transpose_2d fixes + ggml_alloc) (#2852)
|
il y a 2 ans |
 Shouzheng Liu
|
b91ad7f461
ggml-alloc : enlarge size of parse_seq (#2776)
|
il y a 2 ans |
|
Shouzheng Liu
|
38b16dfca6
metal : bug-fix when enable ggml-alloc (#2757)
|
il y a 2 ans |
|
Georgi Gerganov
|
cf658adc83
llm : add Falcon support (#2717)
|
il y a 2 ans |
|
Georgi Gerganov
|
ef3f333d37
ggml : sync latest (SAM + SD operators, CUDA alibi) (#2709)
|
il y a 2 ans |
|
Shouzheng Liu
|
a872a2b28e
ggml-alloc : fix discrepency between measure&eval (#2639)
|
il y a 2 ans |
|
Shouzheng Liu
|
fc8ef549e5
metal : enable ggml-alloc (#2627)
|
il y a 2 ans |
 Sam Spilsbury
|
916a9acdd0
ggml-alloc: Don't try to re-use buffers of external tensors (#2562)
|
il y a 2 ans |
|
slaren
|
a113689571
ggml : add graph tensor allocator (#2411)
|
il y a 2 ans |
