summaryrefslogtreecommitdiff
path: root/tests
AgeCommit message (Expand)Author
2022-11-03Added FP8 quantization map.Tim Dettmers
2022-10-25Added CUDA SETUP instruction generator.Tim Dettmers
2022-10-24Isolated CUDASetup logging; all tests green.Tim Dettmers
2022-09-20try fp32justheuristic
2022-09-20set thresholdTim Dettmers
2022-09-20reviewjustheuristic
2022-09-18cast devicejustheuristic
2022-09-18cast devicejustheuristic
2022-09-18cast devicejustheuristic
2022-09-18cast devicejustheuristic
2022-09-18cast devicejustheuristic
2022-09-18cast before allclosejustheuristic
2022-09-18cast before allclosejustheuristic
2022-09-18debugjustheuristic
2022-09-18pre-castjustheuristic
2022-09-18debugjustheuristic
2022-09-18run backwardjustheuristic
2022-09-18add memory efficient backwardjustheuristic
2022-09-18bump threshold to 0.21justheuristic
2022-09-18more lenient thresholdjustheuristic
2022-09-18cast properlyjustheuristic
2022-09-17un-fuse biasjustheuristic
2022-09-17copypaste tolerancesjustheuristic
2022-09-17clearer assertionsjustheuristic
2022-09-17check dtypes firstjustheuristic
2022-09-17check dtypes firstjustheuristic
2022-09-17cast to half before double_quantjustheuristic
2022-09-17test_bf16justheuristic
2022-09-13Fixed cpu blockwise quantization for small input tensors.Tim Dettmers
2022-09-11Fixed 2^31 max size issue for cpu blockwise quant.Tim Dettmers
2022-08-23Some initial code. Needs to be tested.Tim Dettmers
2022-08-17Fixed bug in Linear8bitLt, when the bias is None.Tim Dettmers
2022-08-16Added fused bias to matmullt.Tim Dettmers
2022-08-16Added fused bias in dequant_mm.Tim Dettmers
2022-08-16Removed storage() from get_ptr; added boilerplate for bias dequant_mm.Tim Dettmers
2022-08-05Added the case that all env variables are empty (CUDA docker).Tim Dettmers
2022-08-04Fixed bugs in cuda setup.Tim Dettmers
2022-08-04Merge branch 'debug' into cuda-bin-switch-and-cliTim Dettmers
2022-08-04Merge branch 'extract_outliers' into debugTim Dettmers
2022-08-03Added fixes for the case that matmullt dim A is zero, e.g. [0, 768].Tim Dettmers
2022-08-02factored cuda_setup.main out into smaller modules and functionsTitus von Koeller
2022-08-01Added some more docs and comments.Tim Dettmers
2022-08-01Added full env variable search; CONDA_PREFIX priority.Tim Dettmers
2022-08-01reran black with linelength 80 for greater readabilityTitus von Koeller
2022-08-01ran black and isort for coherent code formattingTitus von Koeller
2022-07-31Full evaluate_cuda setup with integration test.Tim Dettmers
2022-07-27adding CLI tool for CUDA install debugging - intermediate commitTitus von Koeller
2022-07-26Merge branch 'patch_merge' into extract_outliersTim Dettmers
2022-07-26Added col_ampere outlier extraction kernel.Tim Dettmers
2022-07-26Working outlier extraction for Turing.Tim Dettmers