| .. |
|
ggml-alloc.c
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-alloc.h
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-cuda.cu
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-cuda.h
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-metal.h
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-metal.m
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-metal.metal
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-mpi.c
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-mpi.h
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-opencl.cpp
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml-opencl.h
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml.c
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
ggml.go
|
ggml: fix off by one error
|
2023-08-11 10:45:22 -07:00 |
|
ggml.h
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
k_quants.c
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
k_quants.h
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
llama-util.h
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
llama.cpp
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
llama.go
|
log embedding eval timing
|
2023-08-14 12:51:31 -03:00 |
|
llama.h
|
update `llama.cpp` to `f64d44a`
|
2023-08-12 22:47:15 -04:00 |
|
llama_darwin.go
|
partial decode ggml bin for more info
|
2023-08-10 09:23:10 -07:00 |
|
llm.go
|
implement loading ggml lora adapters through the modelfile
|
2023-08-10 09:23:39 -07:00 |
|
update-llama-cpp.sh
|
partial decode ggml bin for more info
|
2023-08-10 09:23:10 -07:00 |
|
utils.go
|
partial decode ggml bin for more info
|
2023-08-10 09:23:10 -07:00 |
56fd4e4ef2