Daniel Hiltgen 5445aaa94e Add back memory escape valve ...

If we get our predictions wrong, this can be used to
set a lower memory limit as a workaround.  Recent multi-gpu
refactoring accidentally removed it, so this adds it back.

2024-04-23 17:09:02 -07:00

..

ext_server

Support unicode characters in model path (#3681)

2024-04-16 17:00:12 -04:00

generate

Move nested payloads to installer and zip file on windows

2024-04-23 16:14:47 -07:00

llama.cpp @ 7593639ce3

update llama.cpp submodule to 7593639 (#3665)

2024-04-15 23:04:43 -04:00

patches

Bump to b2581

2024-04-02 11:53:07 -07:00

ggla.go

refactor tensor query

2024-04-10 11:37:20 -07:00

ggml.go

fix: mixtral graph

2024-04-22 17:19:44 -07:00

gguf.go

fix padding to only return padding

2024-04-16 15:43:26 -07:00

llm_darwin_amd64.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

llm_darwin_arm64.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

llm_linux.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

llm_windows.go

Move nested payloads to installer and zip file on windows

2024-04-23 16:14:47 -07:00

llm.go

cgo quantize

2024-04-08 15:31:08 -07:00

memory.go

Add back memory escape valve

2024-04-23 17:09:02 -07:00

payload.go

Move nested payloads to installer and zip file on windows

2024-04-23 16:14:47 -07:00

server.go

Detect and recover if runner removed

2024-04-23 10:05:26 -07:00

status.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00