- 09 Aug, 2024 2 commits
-
-
Nicholas Schwab authored
This partially reverts b732beba. It seems like explicitly setting all files to use line feeds was done due to issues with the go linter, hence it can be restricted to those files (https://github.com/ollama/ollama/pull/6235#issuecomment-2278745953).
-
Nicholas42 authored
-
- 07 Aug, 2024 2 commits
-
-
Nicholas Schwab authored
The change b732beba makes all files text files and sets lf as eol. This will automatically change all files to have lf if they are touched by git (e.g. via git status). This change cannot be stashed and makes it hard to work with the repo (rebase and checkout don't really work). See also #6183. Here, we set the offending files (*.png and *.ico, but that might be more in the future) to be treated as binary files and not be changed by git.
-
Jeffrey Morgan authored
-
- 06 Aug, 2024 4 commits
-
-
Jeffrey Morgan authored
-
Chua Chee Seng authored
-
Daniel Hiltgen authored
Ensure sparse files on windows during download
-
Daniel Hiltgen authored
The file.Truncate call on windows will write the whole file unless you set the sparse flag, leading to heavy I/O at the beginning of download. This should improve our I/O behavior on windows and put less stress on the users disk.
-
- 05 Aug, 2024 9 commits
-
-
royjhan authored
-
Michael Yang authored
fix concurrency test
-
Michael Yang authored
-
Daniel Hiltgen authored
Implement linux NUMA detection
-
Michael Yang authored
use testing tempdirs
-
Daniel Hiltgen authored
If the system has multiple numa nodes, enable numa support in llama.cpp If we detect numactl in the path, use that, else use the basic "distribute" mode.
-
Michael Yang authored
line feed
-
frob authored
Users using `journalctl` to get logs for issue logging sometimes don't realize that paging is causing information to be missed.
-
Michael Yang authored
-
- 04 Aug, 2024 1 commit
-
-
sryu1 authored
-
- 03 Aug, 2024 1 commit
-
-
Ivan Charapanau authored
-
- 02 Aug, 2024 5 commits
-
-
Michael Yang authored
-
Michael Yang authored
enable gofmt/gofumpt/goimports/tenv
-
royjhan authored
* Update docs * token bug corrected * Update docs/openai.md * Update docs/openai.md * add suffix * merge conflicts * merge conflicts
-
royjhan authored
-
Michael Yang authored
-
- 01 Aug, 2024 13 commits
-
-
Kim Hallberg authored
-
royjhan authored
* docs without usage * no usage * rm metric note
-
royjhan authored
-
royjhan authored
* add prompt tokens to embed response * rm slog * metrics * types * prompt n * clean up * reset submodule * add tokens to v1/embeddings * separate usage
-
royjhan authored
* OpenAI Docs * Update docs/openai.md Co-authored-by:
Jeffrey Morgan <jmorganca@gmail.com> * Remove newline --------- Co-authored-by:
Jeffrey Morgan <jmorganca@gmail.com>
-
Michael Yang authored
Fix context in /api/generate grows too much (#5980).
-
Michael Yang authored
refactor convert
-
Vyacheslav Moskalev authored
-
Vyacheslav Moskalev authored
-
Vyacheslav Moskalev authored
-
Vyacheslav Moskalev authored
-
Vyacheslav Moskalev authored
-
Michael Yang authored
fix modelfile message quotes
-
- 31 Jul, 2024 3 commits
-
-
Michael Yang authored
-
Michael Yang authored
patches: phi3 optional sliding window attention
-
Blake Mizerany authored
-