 Georgi Gerganov
|
17880771ad
sync : ggml
|
1 year ago |
 Daniel Bevenius
|
55951c018d
ggml : fix typo in example usage ggml_gallocr_new (ggml/984)
|
1 year ago |
 Diego Devesa
|
ff565769f2
ggml : fixes after sync (ggml/983)
|
1 year ago |
 Xuan Son Nguyen
|
f3fdcfaa79
ci : fine-grant permission (#9710)
|
1 year ago |
 Daniel Kleine
|
133c7b46b3
Fixed RNG seed docs (#9723)
|
1 year ago |
|
Georgi Gerganov
|
d5ed2b929d
metal : remove abort (skip) (ggml/0)
|
1 year ago |
|
Georgi Gerganov
|
1bb8a64ebf
sync : ggml
|
1 year ago |
 Johannes Gäßler
|
fabdc3bda3
ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
|
1 year ago |
|
Johannes Gäßler
|
eee39bdc96
ggml: refactor cross entropy loss CPU impl. (ggml/976)
|
1 year ago |
 Jack Mousseau
|
5d5ab1e5cc
metal : fix compute pass descriptor autorelease crash (#9718)
|
1 year ago |
|
Diego Devesa
|
a7ad553513
ggml-backend : add device description to CPU backend (#9720)
|
1 year ago |
 bandoti
|
d6fe7abf04
ggml: unify backend logging mechanism (#9709)
|
1 year ago |
 compilade
|
e3c355ba65
convert : handle tokenizer merges format from transformers 4.45 (#9696)
|
1 year ago |
 Radoslav Gerganov
|
841713e1e4
rpc : enable vulkan (#9714)
|
1 year ago |
 Ouadie EL FAROUKI
|
5639971466
Fixed dequant precision issues in Q4_1 and Q5_1 (#9711)
|
1 year ago |
|
Diego Devesa
|
c83ad6d01e
ggml-backend : add device and backend reg interfaces (#9707)
|
1 year ago |
|
Xuan Son Nguyen
|
a39ab216aa
llama : reduce compile time and binary size (#9712)
|
1 year ago |
 Alberto Cabrera Pérez
|
f536f4c439
[SYCL] Initial cmake support of SYCL for AMD GPUs (#9658)
|
1 year ago |
|
Radoslav Gerganov
|
00b7317e63
vulkan : do not use tensor->extra (#9407)
|
1 year ago |
 Zhenwei Jin
|
76b37d1541
gguf-split : improve --split and --merge logic (#9619)
|
1 year ago |
|
Georgi Gerganov
|
148844fe97
examples : remove benchmark (#9704)
|
1 year ago |
 Paweł Wodnicki
|
3f1ae2e32c
Update README.md (#9591)
|
1 year ago |
|
Georgi Gerganov
|
f1b8c42711
sync : ggml
|
1 year ago |
|
Johannes Gäßler
|
e98c1c188e
test: fix OPT_STEP_ADAMW for test-backend-ops (ggml/974)
|
1 year ago |
 Salvatore Mesoraca
|
cb00020504
vulkan : mul_mat: fix UB with small warps (ggml/952)
|
1 year ago |
 Borislav Stanimirov
|
6c5322481a
ggml : fix ggml_cast (ggml/973)
|
1 year ago |
|
Johannes Gäßler
|
7254cdf7e8
ggml: fix gradient allocation logic (ggml/966)
|
1 year ago |
|
Georgi Gerganov
|
cad341d889
metal : reduce command encoding overhead (#9698)
|
1 year ago |
|
Georgi Gerganov
|
a90484c6d9
llama : print correct model type for Llama 3.2 1B and 3B
|
1 year ago |
|
compilade
|
1927378bcc
convert : refactor rope_freqs generation (#9396)
|
1 year ago |
