mrq/bitsandbytes-rocm
1
0
Fork 1
Code Issues 1 Pull Requests Packages Projects Releases Wiki Activity
278 Commits 2 Branches 0 Tags 1.2 MiB
0f9d30207f
Commit Graph

190 Commits

Author SHA1 Message Date
justheuristic
e9b87112ee un-fuse bias 2022-09-17 23:51:28 +03:00
justheuristic
56a074f6dc un-fuse bias 2022-09-17 23:46:37 +03:00
justheuristic
d9ca0ed905 un-fuse bias 2022-09-17 23:44:28 +03:00
justheuristic
eac9aca460 cast bias too 2022-09-17 23:38:09 +03:00
justheuristic
a9fe0ff98c recast to fp16 2022-09-17 23:34:22 +03:00
justheuristic
fc4a135ed1 clearer assertions 2022-09-17 23:24:26 +03:00
justheuristic
cc4858c2fd some kind of warning or something when this is first executed to make people aware that a cast happens and the operation quantization is performed in fp16. 2022-09-17 20:46:04 +03:00
justheuristic
3634fc738b
Merge branch 'TimDettmers:main' into memory-efficient-backward 2022-09-17 18:42:22 +03:00
Tom Aarsen
58aa7c53f6 Perform check using implicit list length 
Instead of 'ccs is not None', as ccs is always a list, so this if is currently always True
 2022-09-15 12:44:09 +02:00
Tom Aarsen
7d771d1d6d Catch OSError with specific error number 2022-09-15 11:13:12 +02:00
Tom Aarsen
a58cc5a13c Prevent OSError when env variables contain long value 2022-09-15 10:57:49 +02:00
Tim Dettmers
8ccc0b0ee1 Merge branch 'main' of github.com:TimDettmers/bitsandbytes into main 2022-09-11 11:58:40 -07:00
Tim Dettmers
19a7adca7a Fixed 2^31 max size issue for cpu blockwise quant. 2022-09-11 11:55:09 -07:00
dbaranchuk
e2a75769f2 bug fix 2022-09-11 21:41:46 +03:00
dbaranchuk
4dd475ced4 refactoring 2022-09-11 06:28:17 +03:00
dbaranchuk
d358999e9e refactoring 2022-09-11 06:26:15 +03:00
dbaranchuk
ee325f0215 clarified an exception message 2022-09-11 06:18:44 +03:00
dbaranchuk
42b5fc9acc add memory effcient backward option 2022-09-11 05:51:29 +03:00
Dmitry Baranchuk
843ad0631c
Merge pull request #1 from TimDettmers/main 
Update main branch
 2022-09-10 19:33:21 -07:00
Tim Dettmers
2e630b55f5 Version bump + bnb.utils import fix. 2022-09-08 13:16:16 -07:00
Tim Dettmers
aca55881b9
Merge branch 'main' into remove_unused_code 2022-09-05 16:29:25 -07:00
dbaranchuk
8d34d36f15 req_gradA for casted & more efficient and accurate fp16 backward 2022-08-29 00:56:08 +03:00
dbaranchuk
b3fee1ed6a add dtype <-> fp16 cast 2022-08-26 04:11:40 +03:00
dbaranchuk
4d6174bc63 memory efficient fp16 backward 2022-08-25 19:09:23 +03:00
Max Ryabinin
92a3363096 Replace print_stderr with warnings.warn 2022-08-24 18:45:17 +03:00
Max Ryabinin
9fc0ab415c Remove unused code 2022-08-24 18:43:18 +03:00
Tim Dettmers
ee5b947e63 Fixed issue where Pascal was not displaying proper error. 2022-08-23 16:00:26 -07:00
dbaranchuk
ef2936a90d delete CxB from state 2022-08-24 01:33:04 +03:00
dbaranchuk
876387dc0c minor fixes 2022-08-24 01:12:48 +03:00
Tim Dettmers
7e0fb655e1 Some initial code. Needs to be tested. 2022-08-23 13:59:34 -07:00
dbaranchuk
656de8ed11 minor fixes 2022-08-23 23:53:43 +03:00
dbaranchuk
1753aa0418 refactoring 2022-08-23 23:51:00 +03:00
dbaranchuk
8ae9bb23ad add memory efficient backward 2022-08-23 23:39:54 +03:00
Tim Dettmers
9d60b3c527 Fixed bug in Linear8bitLt, when the bias is None. 2022-08-17 03:45:57 -07:00
Tim Dettmers
a6664de072 Enhanced error handling in CUDA SETUP failures. 2022-08-16 19:03:19 -07:00
Tim Dettmers
de354f7ded Added fused bias to matmullt. 2022-08-16 12:00:54 -07:00
Tim Dettmers
111b876449 Merge branch 'cuda-bin-switch-and-cli' of github.com:TimDettmers/bitsandbytes into cuda-bin-switch-and-cli 2022-08-16 10:57:10 -07:00
Tim Dettmers
1ed2fa2f21 Removed storage() from get_ptr; added boilerplate for bias dequant_mm. 2022-08-16 10:56:17 -07:00
Tim Dettmers
1ced47c504 Added CUDA version warning and fixed cuda_install for 9.2/10.2. 2022-08-09 20:02:47 -07:00
Tim Dettmers
f9cbe2fe99 Fixed prod Python < 3.7 compatibility in function.py. 2022-08-08 09:13:22 -07:00
Tim Dettmers
62441815bc Removed prod for Python <= 3.7 compatibility. 2022-08-08 05:20:36 -07:00
Tim Dettmers
26efb154c8 Fixed bug where python -m bitsandbytes was failing. 2022-08-07 09:49:36 -07:00
Tim Dettmers
c472bd56f0 Added the case that all env variables are empty (CUDA docker). 2022-08-05 08:57:52 -07:00
Tim Dettmers
e35337f05e Now determining cuda version via libcudart.so call. 2022-08-05 07:13:24 -07:00
Tim Dettmers
8f84674d67 Fixed bugs in cuda setup. 2022-08-04 09:16:00 -07:00
Tim Dettmers
758c7175a2 Merge branch 'debug' into cuda-bin-switch-and-cli 2022-08-04 08:03:00 -07:00
Tim Dettmers
ab72a1294f Added pre/post device call for extract outliers. 2022-08-04 07:47:22 -07:00
Tim Dettmers
cc5b323876 Merge branch 'extract_outliers' into debug 2022-08-04 07:40:48 -07:00
Tim Dettmers
6101a8fb9f Added pre and post device call to transform. 2022-08-04 07:28:12 -07:00
Tim Dettmers
320eacb4c2 Removed print statement. 2022-08-03 14:17:54 -07:00
Tim Dettmers
451fd9506e Added fixes for the case that matmullt dim A is zero, e.g. [0, 768]. 2022-08-03 11:54:01 -07:00
Tim Dettmers
2f01865a2f Added CUDA block assert and is_on_gpu check. 2022-08-03 09:05:37 -07:00
Titus von Koeller
96bc209baf tentative refactoring of the compute capabilities code 2022-08-02 21:27:36 -07:00
Titus von Koeller
59a615b386 factored cuda_setup.main out into smaller modules and functions 2022-08-02 21:26:50 -07:00
Titus von Koeller
3809236428 move cuda_setup code into subpackage 2022-08-02 07:42:27 -07:00
Tim Dettmers
e120c4a550 Fixed syntax error; bumped revision for beta release. 2022-08-01 20:05:03 -07:00
Tim Dettmers
3479d02a76 Added some more docs and comments. 2022-08-01 19:43:09 -07:00
Tim Dettmers
8bf3e9faab Added full env variable search; CONDA_PREFIX priority. 2022-08-01 19:22:41 -07:00
Titus von Koeller
c4fe6c69a3 deleted function that was moved but accidentally not removed in commit 2022-08-01 09:40:41 -07:00
Titus von Koeller
ea7c14f8ef reran black with linelength 80 for greater readability 2022-08-01 09:32:47 -07:00
Titus von Koeller
3fd06fb620 refactored subshell execution code for greater readability and moved it to utils 2022-08-01 09:30:29 -07:00
Titus von Koeller
bfa0e33294 ran black and isort for coherent code formatting 2022-08-01 03:31:48 -07:00
Titus von Koeller
597a8521b2 fix typo 2022-08-01 03:22:44 -07:00
Titus von Koeller
57fa64628f minor refactor to more concise syntax 2022-08-01 03:22:12 -07:00
Tim Dettmers
28d1e7dc01 Initial build script changes (untested on PyPi). 2022-07-31 19:41:56 -07:00
Tim Dettmers
dd50382b32 Full evaluate_cuda setup with integration test. 2022-07-31 17:47:44 -07:00
Titus von Koeller
5d90b38c4d adding CLI tool for CUDA install debugging - intermediate commit 2022-07-27 21:16:04 -07:00
Tim Dettmers
389f66ca5a Fixed direct extraction masking. 2022-07-27 01:46:35 -07:00
Tim Dettmers
5737f2b027 Merge branch 'patch_merge' into extract_outliers 2022-07-26 19:38:01 -07:00
Tim Dettmers
47a73d94c3 Matmullt with direct outlier extraction for 8-bit inference. 2022-07-26 19:15:35 -07:00
Tim Dettmers
cbb901ac51 Boilerplate and test for extract_outliers. 2022-07-26 12:12:38 -07:00
Tim Dettmers
1e88edd8c0 Removed rowscale (segfaults on ampere). 2022-07-25 17:27:57 -07:00
Tim Dettmers
c771b3a75a Most tests passing. 2022-07-22 14:41:05 -07:00
Max Ryabinin
e4cf33f2a3 Fix imports 2022-07-01 17:25:44 +03:00
Max Ryabinin
8258b4364a Add a CPU-only build option 2022-07-01 17:16:10 +03:00
Max Ryabinin
33efe4a09f Remove unused imports, fix NotImplementedError 2022-06-30 18:14:20 +03:00
Tim Dettmers
20e1677dfd Added module override, bnb.nn.Embedding #13 #15 #19 2021-11-29 09:32:13 -08:00
Tim Dettmers
3cff6795fb Merge branch 'main' of github.com:facebookresearch/bitsandbytes into 0.26.0 2021-11-29 08:24:17 -08:00
Tim Dettmers
108cf9fc1f Fixed unsafe use of eval. #8 2021-11-29 08:21:05 -08:00
Tim Dettmers
2f8083bd8b Added AdamW. #10 #13 2021-11-28 21:18:11 -08:00
Robin Schmidt
67a1283501 [FIX] passing of sparse in StableEmbedding 2021-11-15 17:27:02 +01:00
Tim Dettmers
8b3c0f355c Added adagrad with tests (no clipping). 2021-11-10 15:10:02 -08:00
Konstantin Ditschuneit
56f5274848 Add missing imports to adam 2021-10-31 16:38:38 +01:00
Tim Dettmers
0c5fa5a637 Fixed syntax and import error. 2021-10-21 16:04:18 -07:00
Tim Dettmers
1ec0d54529 Added analysis Adam. 2021-10-21 15:53:20 -07:00
Tim Dettmers
eaf35ab949 Copied over Analysis Adam. 2021-10-21 10:20:41 -07:00
Tim Dettmers
a6eae2e7f2 Added skip_zeros; tests are passing. 2021-10-20 19:15:47 -07:00
Tim Dettmers
bb34fd50a1 Initial plumbing for skip_zeros. 2021-10-20 18:37:44 -07:00
Tim Dettmers
7923c4a066 Changed from testpypi to pypi. Release 0.0.24 2021-10-07 08:39:38 -07:00
Tim Dettmers
7439924891 Initial commit 2021-10-05 19:16:20 -07:00