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