.. |
llama.cpp
|
13ba6df5ab
enable cpu instructions on intel macs
|
1 年之前 |
falcon.go
|
c02c0cd483
starcoder
|
1 年之前 |
ggml.go
|
125d0a013a
ggufv3
|
1 年之前 |
gguf.go
|
c5e1bbabda
instead of static number of parameters for each model family, get the real number from the tensors (#1022)
|
1 年之前 |
llama.go
|
a3fcecf943
only set `main_gpu` if value > 0 is provided
|
1 年之前 |
llm.go
|
19b7a4d715
recent llama.cpp update added kernels for fp32, q5_0, and q5_1
|
1 年之前 |
starcoder.go
|
c02c0cd483
starcoder
|
1 年之前 |
utils.go
|
fccf8d179f
partial decode ggml bin for more info
|
1 年之前 |