Autor | SHA1 Nachricht | Datum |
---|---|---|
|
00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama | vor 5 Monaten |
|
6671e3a162 feat: add CPU offloading support (#598) | vor 6 Monaten |
|
497bf64942 chore: simplify pipeline parallel code in llama | vor 6 Monaten |
|
4599c98f99 feat: dynamic image size support for VLMs | vor 6 Monaten |