Michael Yang 291c663865 fix: clip memory leak

2024-03-14 13:12:42 -07:00

..

ext_server

chore: fix typo (#3073)

2024-03-12 14:09:22 -04:00

generate

update llama.cpp submodule to ceca1ae (#3064)

2024-03-11 12:57:48 -07:00

llama.cpp @ ceca1aef07

update llama.cpp submodule to ceca1ae (#3064)

2024-03-11 12:57:48 -07:00

patches

fix: clip memory leak

2024-03-14 13:12:42 -07:00

dyn_ext_server.c

Revamp ROCm support

2024-03-07 10:36:50 -08:00

dyn_ext_server.go

token repeat limit for prediction requests (#3080)

2024-03-12 22:08:25 -04:00

dyn_ext_server.h

Always dynamically load the llm server library

2024-01-11 08:42:47 -08:00

ggla.go

decode ggla

2024-03-08 15:46:25 -08:00

ggml.go

decode ggla

2024-03-08 15:46:25 -08:00

gguf.go

decode ggla

2024-03-08 15:46:25 -08:00

llama.go

use llm.ImageData

2024-01-31 19:13:48 -08:00

llm.go

disable gpu for certain model architectures and fix divide-by-zero on memory estimation

2024-03-09 12:51:38 -08:00

payload_common.go

update llama.cpp submodule to 77d1ac7 (#3030)

2024-03-09 15:55:34 -08:00

payload_darwin_amd64.go

update llama.cpp submodule to 77d1ac7 (#3030)

2024-03-09 15:55:34 -08:00

payload_darwin_arm64.go

Add multiple CPU variants for Intel Mac

2024-01-17 15:08:54 -08:00

payload_linux.go

Revamp ROCm support

2024-03-07 10:36:50 -08:00

payload_test.go

Fix up the CPU fallback selection

2024-01-11 15:27:06 -08:00

payload_windows.go

Add multiple CPU variants for Intel Mac

2024-01-17 15:08:54 -08:00

utils.go

…