 Matteo Mortari
|
911b437f22
gguf-py : fix double call to add_architecture() (#8952)
|
1 year ago |
 Georgi Gerganov
|
b72942fac9
Merge commit from fork
|
1 year ago |
 fairydreaming
|
6afd1a99dc
llama : add support for lora adapters in T5 model (#8938)
|
1 year ago |
|
Georgi Gerganov
|
272e3bd95e
make : fix llava obj file race (#8946)
|
1 year ago |
|
Georgi Gerganov
|
45a55b91aa
llama : better replace_all (cont) (#8926)
|
1 year ago |
 tc-mb
|
3071c0a5f2
llava : support MiniCPM-V-2.5 (#7599)
|
1 year ago |
|
Georgi Gerganov
|
4305b57c80
sync : ggml
|
1 year ago |
 Matt Stephenson
|
70c0ea3560
whisper : use vulkan as gpu backend when available (whisper/2302)
|
1 year ago |
 Daniel Bevenius
|
5b2c04f492
embedding : add --pooling option to README.md [no ci] (#8934)
|
1 year ago |
|
Daniel Bevenius
|
6f6496bb09
llama : fix typo in llama_tensor_get_type comment [no ci] (#8937)
|
1 year ago |
 Mathieu Geli
|
daef3ab233
server : add one level list nesting for embeddings (#8936)
|
1 year ago |
 compilade
|
345a686d82
llama : reduce useless copies when saving session (#8916)
|
1 year ago |
|
compilade
|
3a14e00366
gguf-py : simplify support for quant types (#8838)
|
1 year ago |
|
Georgi Gerganov
|
afd27f01fe
scripts : sync cann files (#0)
|
1 year ago |
|
Georgi Gerganov
|
366d486c16
scripts : fix sync filenames (#0)
|
1 year ago |
|
Georgi Gerganov
|
e44a561ab0
sync : ggml
|
1 year ago |
 Borislav Stanimirov
|
f93d49ab1e
ggml : ignore more msvc warnings (ggml/906)
|
1 year ago |
|
Georgi Gerganov
|
5b33ea1ee7
metal : fix struct name (ggml/912)
|
1 year ago |
 Conrad Kramer
|
85fca8deb6
metal : add abort callback (ggml/905)
|
1 year ago |
 Pablo Duboue
|
ebd541a570
make : clean llamafile objects (#8923)
|
1 year ago |
 slaren
|
15fa07a5c5
make : use C compiler to build metal embed object (#8899)
|
1 year ago |
|
slaren
|
be55695eff
ggml-backend : fix async copy from CPU (#8897)
|
1 year ago |
 Ouadie EL FAROUKI
|
0478174d59
[SYCL] Updated SYCL device filtering (#8901)
|
1 year ago |
 Johannes Gäßler
|
a8dbc6f753
CUDA/HIP: fix tests/test-backend-ops (#8896)
|
1 year ago |
 Zhenwei Jin
|
506122d854
llama-bench : add support for getting cpu info on Windows (#8824)
|
1 year ago |
|
Daniel Bevenius
|
725e3d9437
quantize : update usage comment in quantize.cpp (#8889)
|
1 year ago |
 Nexes the Old
|
31958546c3
typo correction (#8891)
|
1 year ago |
 Xuan Son Nguyen
|
1e6f6554aa
server : add lora hotswap endpoint (WIP) (#8857)
|
1 year ago |
|
Johannes Gäßler
|
641f5dd2a6
CUDA: fix padding logic for FP16/FP32 (#8884)
|
1 year ago |
|
Daniel Bevenius
|
5f4dcb1e60
simple : update name of executable to llama-simple (#8885)
|
1 year ago |
