- 04 Jan, 2024 1 commit
-
-
Daniel Hiltgen authored
Go embed doesn't like when there's no matching files, so put a dummy placeholder in to allow building without any GPU support If no "server" library is found, it's safely ignored at runtime.
-
- 03 Jan, 2024 10 commits
-
-
Jeffrey Morgan authored
-
Bruce MacDonald authored
-
Daniel Hiltgen authored
Fix windows system memory lookup
-
Daniel Hiltgen authored
This refines the gpu package error handling and fixes a bug with the system memory lookup on windows.
-
Daniel Hiltgen authored
Refactor how we augment llama.cpp and refine windows native build
-
Bruce MacDonald authored
-
Cole Gillespie authored
-
Jeffrey Morgan authored
-
Patrick Devine authored
-
Jeffrey Morgan authored
-
- 02 Jan, 2024 6 commits
-
-
Daniel Hiltgen authored
This one log line was triggering a single line llama.log to be generated in the pwd of the server
-
Daniel Hiltgen authored
-
Daniel Hiltgen authored
Refactor where we store build outputs, and support a fully dynamic loading model on windows so the base executable has no special dependencies thus doesn't require a special PATH.
-
Daniel Hiltgen authored
This changes the model for llama.cpp inclusion so we're not applying a patch, but instead have the C++ code directly in the ollama tree, which should make it easier to refine and update over time.
-
Karim ElGhandour authored
-
Dane Madsen authored
-
- 27 Dec, 2023 3 commits
-
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
- 25 Dec, 2023 1 commit
-
-
Icelain authored
-
- 24 Dec, 2023 1 commit
-
-
Jeffrey Morgan authored
-
- 23 Dec, 2023 3 commits
-
-
Jeffrey Morgan authored
-
Daniel Hiltgen authored
Guard integration tests with a tag
-
Daniel Hiltgen authored
This should help CI avoid running the integration test logic in a container where it's not currently possible.
-
- 22 Dec, 2023 13 commits
-
-
K0IN authored
-
Bruce MacDonald authored
-
Jeffrey Morgan authored
-
Matt Williams authored
update where are models stored q
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Matt Williams authored
Most of the examples needed updates of Readmes to show how to run them. Some of the requirements.txt files had extra content that wasn't needed, or missing altogether. Apparently some folks like to run npm start to run typescript, so a script was added to all typescript examples which hadn't been done before. Basically just a lot of cleanup. Signed-off-by: -
Matt Williams authored
* Clean up documentation Will probably need to update with PRs for new release. Signed-off-by:
Jeffrey Morgan <jmorganca@gmail.com> * addressing comments Signed-off-by:
-
Daniel Hiltgen authored
Quiet down llama.cpp logging by default
-
Daniel Hiltgen authored
By default builds will now produce non-debug and non-verbose binaries. To enable verbose logs in llama.cpp and debug symbols in the native code, set `CGO_CFLAGS=-g`
-
Daniel Hiltgen authored
Add cgo implementation for llama.cpp
-
Daniel Hiltgen authored
-
Daniel Hiltgen authored
-
Daniel Hiltgen authored
The default thread count logic was broken and resulted in 2x the number of threads as it should on a hyperthreading CPU resulting in thrashing and poor performance.
-
- 21 Dec, 2023 2 commits
-
-
Bruce MacDonald authored
-
Daniel Hiltgen authored
The windows native setup still needs some more work, but this gets it building again and if you set the PATH properly, you can run the resulting exe on a cuda system.
-
