- 23 May, 2024 1 commit
-
-
Daniel Hiltgen authored
-
- 22 May, 2024 3 commits
-
-
Michael authored
-
Ikko Eltociear Ashimine authored
PreTokenziers -> PreTokenizers
-
Josh authored
add Ctrl + W shortcut
-
- 21 May, 2024 8 commits
-
-
Josh Yan authored
-
Patrick Devine authored
-
Michael Yang authored
simplify safetensors reading
-
Michael Yang authored
Convert directly from llama3
-
Sang Park authored
The spelling of the term "request" has been corrected, which was previously mistakenly written as "requeset" in the error log message.
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
- 20 May, 2024 18 commits
-
-
Michael Yang authored
-
Michael Yang authored
-
Patrick Devine authored
-
Patrick Devine authored
-
Patrick Devine authored
-
Patrick Devine authored
-
Patrick Devine authored
-
Michael Yang authored
fix quantize file types
-
jmorganca authored
-
Josh Yan authored
-
Michael Yang authored
-
Michael Yang authored
-
alwqx authored
-
Michael Yang authored
cache and reuse intermediate blobs
-
Sam authored
* feat: enable flash attention if supported * feat: enable flash attention if supported * feat: enable flash attention if supported * feat: add flash_attn support
-
Michael Yang authored
particularly useful for zipfiles and f16s
-
Patrick Devine authored
-
jmorganca authored
-
- 18 May, 2024 1 commit
-
-
Patrick Devine authored
-
- 17 May, 2024 1 commit
-
-
Daniel Hiltgen authored
Don't return error on signal exit
-
- 16 May, 2024 8 commits
-
-
Daniel Hiltgen authored
Skip max queue test on remote
-
Daniel Hiltgen authored
-
Daniel Hiltgen authored
This test needs to be able to adjust the queue size down from our default setting for a reliable test, so it needs to skip on remote test execution mode.
-
Josh authored
changed line display to be calculated with runewidth
-
Josh Yan authored
-
Rose Heart authored
* Update README.md Added chat/moderation bot to list of software. * Update README.md Fixed link error.
-
Jeffrey Morgan authored
-
Josh Yan authored
-
