 SRHMorris
|
b0915d5b51
vulkan : retry allocation with fallback flags (whisper/2451)
|
1 anno fa |
 Georgi Gerganov
|
8c475b97b8
rerank : use [SEP] token instead of [BOS] (#9737)
|
1 anno fa |
|
Georgi Gerganov
|
58b16695e1
sync : ggml
|
1 anno fa |
|
Georgi Gerganov
|
905f5485b2
metal : zero-init buffer contexts (whisper/0)
|
1 anno fa |
 Viet-Anh NGUYEN (Andrew)
|
71967c2a6d
Add Llama Assistant (#9744)
|
1 anno fa |
|
Georgi Gerganov
|
17880771ad
sync : ggml
|
1 anno fa |
 Daniel Bevenius
|
55951c018d
ggml : fix typo in example usage ggml_gallocr_new (ggml/984)
|
1 anno fa |
 Diego Devesa
|
ff565769f2
ggml : fixes after sync (ggml/983)
|
1 anno fa |
 Xuan Son Nguyen
|
f3fdcfaa79
ci : fine-grant permission (#9710)
|
1 anno fa |
 Daniel Kleine
|
133c7b46b3
Fixed RNG seed docs (#9723)
|
1 anno fa |
|
Georgi Gerganov
|
d5ed2b929d
metal : remove abort (skip) (ggml/0)
|
1 anno fa |
|
Georgi Gerganov
|
1bb8a64ebf
sync : ggml
|
1 anno fa |
 Johannes Gäßler
|
fabdc3bda3
ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
|
1 anno fa |
|
Johannes Gäßler
|
eee39bdc96
ggml: refactor cross entropy loss CPU impl. (ggml/976)
|
1 anno fa |
 Jack Mousseau
|
5d5ab1e5cc
metal : fix compute pass descriptor autorelease crash (#9718)
|
1 anno fa |
|
Diego Devesa
|
a7ad553513
ggml-backend : add device description to CPU backend (#9720)
|
1 anno fa |
 bandoti
|
d6fe7abf04
ggml: unify backend logging mechanism (#9709)
|
1 anno fa |
 compilade
|
e3c355ba65
convert : handle tokenizer merges format from transformers 4.45 (#9696)
|
1 anno fa |
 Radoslav Gerganov
|
841713e1e4
rpc : enable vulkan (#9714)
|
1 anno fa |
 Ouadie EL FAROUKI
|
5639971466
Fixed dequant precision issues in Q4_1 and Q5_1 (#9711)
|
1 anno fa |
|
Diego Devesa
|
c83ad6d01e
ggml-backend : add device and backend reg interfaces (#9707)
|
1 anno fa |
|
Xuan Son Nguyen
|
a39ab216aa
llama : reduce compile time and binary size (#9712)
|
1 anno fa |
 Alberto Cabrera Pérez
|
f536f4c439
[SYCL] Initial cmake support of SYCL for AMD GPUs (#9658)
|
1 anno fa |
|
Radoslav Gerganov
|
00b7317e63
vulkan : do not use tensor->extra (#9407)
|
1 anno fa |
 Zhenwei Jin
|
76b37d1541
gguf-split : improve --split and --merge logic (#9619)
|
1 anno fa |
|
Georgi Gerganov
|
148844fe97
examples : remove benchmark (#9704)
|
1 anno fa |
 Paweł Wodnicki
|
3f1ae2e32c
Update README.md (#9591)
|
1 anno fa |
|
Georgi Gerganov
|
f1b8c42711
sync : ggml
|
1 anno fa |
|
Johannes Gäßler
|
e98c1c188e
test: fix OPT_STEP_ADAMW for test-backend-ops (ggml/974)
|
1 anno fa |
 Salvatore Mesoraca
|
cb00020504
vulkan : mul_mat: fix UB with small warps (ggml/952)
|
1 anno fa |
