Age | Commit message (Collapse) | Author | |
---|---|---|---|
2022-09-13 | Fixed cpu blockwise quantization for small input tensors. | Tim Dettmers | |
2022-09-11 | Fixed 2^31 max size issue for cpu blockwise quant. | Tim Dettmers | |
2022-07-01 | Reduce diff | Max Ryabinin | |
2022-07-01 | Add a CPU-only build option | Max Ryabinin | |