- 15 Oct, 2023 1 commit
-
-
Jeffrey Morgan authored
-
- 14 Oct, 2023 3 commits
-
-
Jeffrey Morgan authored
-
Matt Williams authored
add how to quantize doc
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
- 13 Oct, 2023 10 commits
-
-
Jeffrey Morgan authored
-
Bruce MacDonald authored
-
Michael Yang authored
fix: offloading on low end GPUs
-
Michael Yang authored
-
Michael Yang authored
-
Bruce MacDonald authored
Co-authored-by:Jeffrey Morgan <jmorganca@gmail.com>
-
Bruce MacDonald authored
- remove new lines from llama.cpp error messages relayed to client - check api option types and return error on wrong type - change num layers from 95% VRAM to 92% VRAM
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
- 12 Oct, 2023 11 commits
-
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Michael Yang authored
fix download
-
Michael Yang authored
-
Matt Williams authored
rename the examples to be more descriptive
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Bruce MacDonald authored
-
Bruce MacDonald authored
* give direction to user when runner fails * also relay errors from timeout * increase timeout to 3 minutes
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
- 11 Oct, 2023 14 commits
-
-
Jeffrey Morgan authored
-
Michael Yang authored
Mxyng/more downloads
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
-
Michael Yang authored
cleanup format time
-
Michael Yang authored
-
Bruce MacDonald authored
* update streaming request accept header * add optional stream param to request bodies
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Bruce MacDonald authored
* prevent waiting on exited command * close llama runner once
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
Matt Williams authored
Signed-off-by:Matt Williams <m@technovangelist.com>
-
- 10 Oct, 2023 1 commit
-
-
Bruce MacDonald authored
* check free memory not total * wait for subprocess to exit
-