 Felix
|
104f5e0fc1
clip : fix memory leak (#6138)
|
1 gadu atpakaļ |
 slaren
|
5e1b7f94a0
backend : set max split inputs to GGML_MAX_SRC (#6137)
|
1 gadu atpakaļ |
 Georgi Gerganov
|
ac9ee6a4ad
ci : disable stale issue messages (#6126)
|
1 gadu atpakaļ |
|
Georgi Gerganov
|
4f6d1337ca
ci : temporary disable sanitizer builds (#6128)
|
1 gadu atpakaļ |
|
slaren
|
2bf8d0f7c4
backend : offload large batches to GPU (#6083)
|
1 gadu atpakaļ |
 DAN™
|
496bc79bc2
common : tidy-up argument parsing (#6105)
|
1 gadu atpakaļ |
 Thérence
|
9b03719ad7
convert : add support for CamembertModel architecture (#6119)
|
1 gadu atpakaļ |
 Romain D
|
3a6efdd03c
convert : use f32 outtype for bf16 tensors (#6106)
|
1 gadu atpakaļ |
 Pierrick Hymbert
|
d01b3c4c32
common: llama_load_model_from_url using --model-url (#6098)
|
1 gadu atpakaļ |
|
Georgi Gerganov
|
cd776c37c9
ci : close all stale issues at once (#6115)
|
1 gadu atpakaļ |
 GainLee
|
dc0f612548
ggml:fix finding transfer queue family index error (#6094)
|
1 gadu atpakaļ |
 AmirAli Mirian
|
c47cf414ef
ggml : add AVX512F SIMD (#6088)
|
1 gadu atpakaļ |
 Daniel Bevenius
|
b5f4ae09c3
gritlm : add initial README.md (#6086)
|
1 gadu atpakaļ |
 Xuan Son Nguyen
|
dfbfdd60f9
readme : add wllama as a wasm binding (#6100)
|
1 gadu atpakaļ |
|
DAN™
|
15961ec04d
common : refactor nested if causing error C1061 on MSVC (#6101)
|
1 gadu atpakaļ |
|
Pierrick Hymbert
|
a56d09a440
ci : close inactive issue with workflow (#6053)
|
1 gadu atpakaļ |
|
slaren
|
d84c48505f
llama : fix Baichuan2 13B (#6092)
|
1 gadu atpakaļ |
 Theia Vogel
|
877b4d0c62
llama : add support for control vectors (#5970)
|
1 gadu atpakaļ |
 Andrew Canis
|
12247f4c69
llama : add Command-R support (#6033)
|
1 gadu atpakaļ |
 Ting Lou
|
4e9a7f7f7f
llava : change API to pure C style for Rust FFI bindgen (#6079)
|
1 gadu atpakaļ |
|
slaren
|
3020327f6c
cuda : disable unused cudaLaunchHostFunc code (#6078)
|
1 gadu atpakaļ |
 Neo Zhang Jianyu
|
46acb36767
fix set main gpu error (#6073)
|
1 gadu atpakaļ |
|
Georgi Gerganov
|
131b058409
make : ggml-metal.o depends on ggml.h
|
1 gadu atpakaļ |
 AidanBeltonS
|
753e36f650
[SYCL] Fix non-intel device selection (#6042)
|
1 gadu atpakaļ |
 Ondřej Čertík
|
7ce2c77f88
gguf : add support for I64 and F64 arrays (#6062)
|
1 gadu atpakaļ |
|
Xuan Son Nguyen
|
aab606a11f
llama : add Orion chat template (#6066)
|
1 gadu atpakaļ |
|
slaren
|
b0bc9f4a9d
llama-bench : use random tokens to improve accuracy with mixtral (#6069)
|
1 gadu atpakaļ |
|
Georgi Gerganov
|
4755afd1cb
llama : fix integer overflow during quantization (#6063)
|
1 gadu atpakaļ |
 Steve Grubb
|
6e0438da3c
gguf : fix resource leaks (#6061)
|
1 gadu atpakaļ |
|
Ondřej Čertík
|
727107707a
gguf-py : bump version to 0.8.0 (#6060)
|
1 gadu atpakaļ |
