.. |
ext_server
|
8da7bef05f
Support multiple variants for a given llm lib type
|
1 år sedan |
generate
|
39928a42e8
Always dynamically load the llm server library
|
1 år sedan |
llama.cpp @ 328b83de23
|
f83881390f
revert submodule back to `328b83de23b33240e28f4e74900d1d06726f5eb1`
|
1 år sedan |
dyn_ext_server.c
|
39928a42e8
Always dynamically load the llm server library
|
1 år sedan |
dyn_ext_server.go
|
39928a42e8
Always dynamically load the llm server library
|
1 år sedan |
dyn_ext_server.h
|
39928a42e8
Always dynamically load the llm server library
|
1 år sedan |
ggml.go
|
2bb2bdd5d4
fix lint
|
1 år sedan |
gguf.go
|
08f1e18965
Offload layers to GPU based on new model size estimates (#1850)
|
1 år sedan |
llama.go
|
4a33cede20
remove unused fields and functions
|
1 år sedan |
llm.go
|
d7af35d3d0
import fmt
|
1 år sedan |
payload_common.go
|
d2be6387c9
fix typo
|
1 år sedan |
payload_darwin.go
|
39928a42e8
Always dynamically load the llm server library
|
1 år sedan |
payload_linux.go
|
39928a42e8
Always dynamically load the llm server library
|
1 år sedan |
payload_test.go
|
39928a42e8
Always dynamically load the llm server library
|
1 år sedan |
payload_windows.go
|
39928a42e8
Always dynamically load the llm server library
|
1 år sedan |
utils.go
|
fccf8d179f
partial decode ggml bin for more info
|
1 år sedan |