Jesse Gross ebdf781397 server: Fix double free on runner subprocess error. ...

If the runner subprocess encounters an error, it will close the HTTP
connect, which causes Ollama to free the instance of the model that has
open. When Ollama exits, it will again try to free the models for all
of the runners that were open, resulting in a double free.

2024-09-03 21:15:14 -04:00

..

ext_server

llm: update llama.cpp commit to 8962422 (#6618)

2024-09-03 21:12:39 -04:00

generate

Fix parallel requests

2024-09-03 21:15:13 -04:00

llama.cpp @ 8962422b1c

llm: update llama.cpp commit to 8962422 (#6618)

2024-09-03 21:12:39 -04:00

patches

llm: update llama.cpp commit to 8962422 (#6618)

2024-09-03 21:12:39 -04:00

filetype.go

revert llm changes

2024-09-03 21:15:13 -04:00

ggla.go

update convert test to check result data

2024-07-31 10:59:38 -07:00

ggml_test.go

…

ggml.go

revert llm changes

2024-09-03 21:15:13 -04:00

gguf.go

add conversion for microsoft phi 3 mini/medium 4k, 128

2024-08-12 15:13:29 -07:00

llm_darwin_amd64.go

Enable windows error dialog for subprocess startup

2024-07-22 14:07:27 -07:00

llm_darwin_arm64.go

Enable windows error dialog for subprocess startup

2024-07-22 14:07:27 -07:00

llm_linux.go

Enable windows error dialog for subprocess startup

2024-07-22 14:07:27 -07:00

llm_windows.go

Enable windows error dialog for subprocess startup

2024-07-22 14:07:27 -07:00

llm.go

llm: Fix lint

2024-09-03 21:15:14 -04:00

memory_test.go

llama3.1

2024-08-21 11:49:31 -07:00

memory.go

…

payload.go

Add Jetson cuda variants for arm

2024-08-19 09:38:53 -07:00

server.go

server: Fix double free on runner subprocess error.

2024-09-03 21:15:14 -04:00

status.go

Catch one more error log

2024-08-05 09:28:07 -07:00