Michael Yang
|
125d0a013a
ggufv3
|
1 gadu atpakaļ |
Michael Yang
|
c02c0cd483
starcoder
|
1 gadu atpakaļ |
Bruce MacDonald
|
86279f4ae3
unbound max num gpu layers (#591)
|
1 gadu atpakaļ |
Bruce MacDonald
|
4cba75efc5
remove tmp directories created by previous servers (#559)
|
1 gadu atpakaļ |
Bruce MacDonald
|
66003e1d05
subprocess improvements (#524)
|
1 gadu atpakaļ |
Bruce MacDonald
|
2540c9181c
support for packaging in multiple cuda runners (#509)
|
1 gadu atpakaļ |
Michael Yang
|
7dee25a07f
fix falcon decode
|
1 gadu atpakaļ |
Bruce MacDonald
|
09dd2aeff9
GGUF support (#441)
|
1 gadu atpakaļ |
Michael Yang
|
b1cececb8e
add 34b model type
|
1 gadu atpakaļ |
Michael Yang
|
a894cc792d
model and file type as strings
|
1 gadu atpakaļ |
Michael Yang
|
6ed991c8e2
ggml: fix off by one error
|
1 gadu atpakaļ |
Michael Yang
|
fccf8d179f
partial decode ggml bin for more info
|
1 gadu atpakaļ |