| .. |
|
ext_server
|
53c107e20e
chore: fix typo (#3073)
|
1 year ago |
|
generate
|
369eda65f5
update llama.cpp submodule to `ceca1ae` (#3064)
|
1 year ago |
|
llama.cpp @ ceca1aef07
|
369eda65f5
update llama.cpp submodule to `ceca1ae` (#3064)
|
1 year ago |
|
patches
|
b80661e8c7
relay load model errors to the client (#3065)
|
1 year ago |
|
dyn_ext_server.c
|
6c5ccb11f9
Revamp ROCm support
|
1 year ago |
|
dyn_ext_server.go
|
ca7c3f7e0f
limit `num_predict` to `num_ctx`
|
1 year ago |
|
dyn_ext_server.h
|
39928a42e8
Always dynamically load the llm server library
|
1 year ago |
|
ggla.go
|
76bdebbadf
decode ggla
|
1 year ago |
|
ggml.go
|
76bdebbadf
decode ggla
|
1 year ago |
|
gguf.go
|
76bdebbadf
decode ggla
|
1 year ago |
|
llama.go
|
f11bf0740b
use `llm.ImageData`
|
1 year ago |
|
llm.go
|
f9cd55c70b
disable gpu for certain model architectures and fix divide-by-zero on memory estimation
|
1 year ago |
|
payload_common.go
|
1ffb1e2874
update llama.cpp submodule to `77d1ac7` (#3030)
|
1 year ago |
|
payload_darwin_amd64.go
|
1ffb1e2874
update llama.cpp submodule to `77d1ac7` (#3030)
|
1 year ago |
|
payload_darwin_arm64.go
|
1b249748ab
Add multiple CPU variants for Intel Mac
|
1 year ago |
|
payload_linux.go
|
6c5ccb11f9
Revamp ROCm support
|
1 year ago |
|
payload_test.go
|
7427fa1387
Fix up the CPU fallback selection
|
1 year ago |
|
payload_windows.go
|
1b249748ab
Add multiple CPU variants for Intel Mac
|
1 year ago |
|
utils.go
|
fccf8d179f
partial decode ggml bin for more info
|
1 year ago |
Jeffrey Morgan
ca7c3f7e0f
limit `num_predict` to `num_ctx`