| Age | Commit message (Expand) | Author |
|---|
| 2022-11-07 | Fixed bug in cpu quant; faster GPU dequant. | Tim Dettmers |
| 2022-11-06 | Fixed blockwise test and logic. | Tim Dettmers |
| 2022-11-06 | Added blocksizes 2048, 1024, and 512 to blockwise quant. | Tim Dettmers |
| 2022-11-06 | Added k<256 quantile estimate. | Tim Dettmers |
| 2022-11-06 | Added k-bit fp8 map. | Tim Dettmers |
| 2022-11-06 | Added k-bit linear quantization. | Tim Dettmers |
| 2022-11-03 | Added FP8 quantization map. | Tim Dettmers |
| 2022-10-24 | Isolated CUDASetup logging; all tests green. | Tim Dettmers |
| 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 |
| 2022-08-23 | Some initial code. Needs to be tested. | Tim Dettmers |
| 2022-08-16 | Added fused bias in dequant_mm. | Tim Dettmers |
| 2022-08-16 | Removed storage() from get_ptr; added boilerplate for bias dequant_mm. | Tim Dettmers |
| 2022-08-01 | reran black with linelength 80 for greater readability | Titus von Koeller |
| 2022-08-01 | ran black and isort for coherent code formatting | Titus von Koeller |
| 2022-07-26 | Merge branch 'patch_merge' into extract_outliers | Tim Dettmers |
| 2022-07-26 | Added col_ampere outlier extraction kernel. | Tim Dettmers |
| 2022-07-26 | Working outlier extraction for Turing. | Tim Dettmers |
| 2022-07-26 | Boilerplate and test for extract_outliers. | Tim Dettmers |
| 2022-07-25 | Removed rowscale (segfaults on ampere). | Tim Dettmers |
| 2022-07-25 | Fixed makefile; fixed Ampere igemmlt_8 bug. | Tim Dettmers |
| 2022-07-22 | Most tests passing. | Tim Dettmers |
| 2021-10-05 | Initial commit | Tim Dettmers |
