Stefan Weil
|
abfdc4710f
all: fix typos in documentation, code, and comments (#7021)
|
4 maanden geleden |
Sam
|
1bdab9fdb1
llm: introduce k/v context quantization (vRAM improvements) (#6279)
|
5 maanden geleden |
Daniel Hiltgen
|
05cd82ef94
Rename gpu package discover (#7143)
|
6 maanden geleden |
Michael Yang
|
77903ab8b4
llama3.1
|
9 maanden geleden |
Michael Yang
|
b732beba6a
lint
|
9 maanden geleden |
Michael Yang
|
df993fa37b
comments
|
9 maanden geleden |
Michael Yang
|
5e9db9fb0b
refactor convert
|
11 maanden geleden |
Michael Yang
|
35b89b2eab
rfc: dynamic environ lookup
|
10 maanden geleden |
Blake Mizerany
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
10 maanden geleden |
Daniel Hiltgen
|
6f351bf586
review comments and coverage
|
11 maanden geleden |
Daniel Hiltgen
|
6fd04ca922
Improve multi-gpu handling at the limit
|
11 maanden geleden |