Tim Dettmers
|
ec1ea63711
|
Refactored triton into its own folder. Refactored fp8 matmuls.
|
2023-04-12 09:39:39 -07:00 |
|
Mitchell Wortsman
|
d677a71607
|
typo
|
2023-04-08 19:36:17 +00:00 |
|
Mitchell Wortsman
|
da524d97c9
|
mem efficient"
|
2023-04-08 19:34:18 +00:00 |
|
Mitchell Wortsman
|
eb6c53cf55
|
clarify in readme
|
2023-04-01 23:50:12 +00:00 |
|
Mitchell Wortsman
|
2331212b35
|
add readme for speed bench
|
2023-04-01 19:13:15 +00:00 |
|
Mitchell Wortsman
|
7f87ba83ee
|
cleaning and refactor
|
2023-04-01 18:46:04 +00:00 |
|
Tim Dettmers
|
30d21d585c
|
Added triton test.
|
2023-03-31 11:33:26 -07:00 |
|
Tim Dettmers
|
a13a522c4c
|
Added first triton test.
|
2023-03-31 11:20:54 -07:00 |
|
Mitchell Wortsman
|
b373034e31
|
test
|
2023-03-29 19:04:53 +00:00 |
|
Mitchell Wortsman
|
5f3d9ada8d
|
triton-v1
|
2023-03-29 06:47:08 +00:00 |
|
Mitchell Wortsman
|
51f8bb7133
|
pre-triton update
|
2023-03-24 05:44:42 +00:00 |
|
Mitchell Wortsman
|
75377d125e
|
new experiments
|
2023-02-24 00:10:15 +00:00 |
|
Tim Dettmers
|
5d2e23e8d6
|
Merge branch 'fp8sim' of github.com:TimDettmers/bitsandbytes into fp8sim
|
2023-02-23 10:56:49 -08:00 |
|
Tim Dettmers
|
c5c38ca19c
|
Added matmul_mixed.
|
2023-02-23 10:45:18 -08:00 |
|
Mitchell Wortsman
|
3fbf60ad83
|
sim now worse than real
|
2023-02-23 08:27:15 +00:00 |
|
Mitchell Wortsman
|
7b764d3569
|
adding half() cast
|
2023-02-21 03:53:44 +00:00 |
|
Tim Dettmers
|
2489d819c5
|
Added more blocksizes for stochastic rounding; fixed dequant blocksize.
|
2023-02-14 13:55:17 -08:00 |
|
Tim Dettmers
|
2dfa3ce16d
|
Fixed LinearFP8 and added tests.
|
2023-02-13 17:48:52 -08:00 |
|
Tim Dettmers
|
fa255cbc56
|
Added missing import.
|
2023-02-13 17:29:39 -08:00 |
|
Tim Dettmers
|
ca3236587a
|
Added forward/backward tests; removed bias.
|
2023-02-13 17:20:52 -08:00 |
|
Tim Dettmers
|
6bdb6c351e
|
Added fp8 simulation layer.
|
2023-02-13 16:53:07 -08:00 |
|
Tim Dettmers
|
c9f505064e
|
Added outlier detector and fake quantization layer.
|
2023-01-28 17:05:22 -08:00 |
|
Tim Dettmers
|
1341fb44ad
|
Fixed issue where the CUDA SETUP was not printed.
|
2023-01-04 03:50:53 -08:00 |
|
Tim Dettmers
|
3901ebf7ae
|
Added CUDA 12.0 support; removed CC 3.0 support.
|
2023-01-04 02:28:33 -08:00 |
|
Tim Dettmers
|
b3de19218e
|
Added error message for unexpected CUDA exception.
|
2023-01-03 06:57:07 -08:00 |
|
Tim Dettmers
|
81990491ff
|
Merge pull request #113 from Borzik/fix-warnings
Import missing warn function
|
2023-01-03 15:46:58 +01:00 |
|
Tim Dettmers
|
9180b4cc11
|
Added additional error message for cudart error #85
|
2023-01-03 06:44:11 -08:00 |
|
Tim Dettmers
|
dfb049f8e4
|
Added Python >= 3.8 requirement.
|
2023-01-03 06:20:06 -08:00 |
|
Tim Dettmers
|
211ad594df
|
Added error+instructions for unsupported CUDA 10.0 version #82
|
2023-01-03 06:07:35 -08:00 |
|
Felix Borzik
|
f3800bab75
|
import warn function
|
2023-01-03 13:23:34 +00:00 |
|
Tim Dettmers
|
9d353ca786
|
Merge pull request #87 from lostmsu/main
Add `device` and `dtype` parameters to `StableEmbedding`
|
2023-01-02 13:22:45 +01:00 |
|
Tim Dettmers
|
7a6563b6c8
|
Default to CPU library on CUDA error+small refactor.
|
2023-01-02 03:47:09 -08:00 |
|
Tim Dettmers
|
d9112dc55b
|
Merge pull request #110 from BlackHC/cublaslt_version
Improve cc version detection for cublaslt
|
2023-01-02 12:35:53 +01:00 |
|
Tim Dettmers
|
336e24696c
|
CUDASetup only executed once + fixed circular import.
|
2023-01-02 03:31:43 -08:00 |
|
Tim Dettmers
|
df9a9b0c4c
|
Merge pull request #77 from Cyberes/main
Allow hiding of the welcome message
|
2023-01-02 11:28:17 +01:00 |
|
Tim Dettmers
|
be5cecb88f
|
Merge branch 'main' into main
|
2023-01-02 11:23:17 +01:00 |
|
Tim Dettmers
|
f0ec93d016
|
Merge pull request #76 from tomaarsen/cleanup
Cleanup involving a handful of failures, some optimization and a lot of code quality improvements
|
2023-01-02 11:19:28 +01:00 |
|
Tim Dettmers
|
c91f592ad7
|
Merge branch 'main' into cleanup
|
2023-01-02 11:19:16 +01:00 |
|
blackhc
|
ed17aa9a31
|
Don't mark it as failure though.
|
2022-12-29 23:50:48 +00:00 |
|
blackhc
|
7b39a5511d
|
Fix issue #97
|
2022-12-29 23:47:21 +00:00 |
|
Tim Dettmers
|
c059bd2848
|
Added additional blocksizes: {64, 128, 256}.
|
2022-11-20 14:18:15 -08:00 |
|
Tim Dettmers
|
eb028e6ebc
|
Fixed k-bit quantization maps.
|
2022-11-19 07:24:03 -08:00 |
|
Tom Aarsen
|
b104ce3b62
|
Merge branch 'main' into cleanup
|
2022-11-17 15:22:29 +01:00 |
|
Tim Dettmers
|
08fa2e7b01
|
Fixed bug in cpu quant; faster GPU dequant.
|
2022-11-07 18:06:18 -08:00 |
|
Tim Dettmers
|
62a333ac40
|
Added pre/post calls do quantize_blockwise.
|
2022-11-06 17:17:51 -08:00 |
|
Tim Dettmers
|
e0e697b150
|
Fixed blockwise test and logic.
|
2022-11-06 16:36:31 -08:00 |
|
Tim Dettmers
|
6bc2b992be
|
Added blocksizes 2048, 1024, and 512 to blockwise quant.
|
2022-11-06 16:27:48 -08:00 |
|
Tim Dettmers
|
2f2063bac2
|
Added k<256 quantile estimate.
|
2022-11-06 13:05:25 -08:00 |
|
Tim Dettmers
|
98cbc4bc4f
|
Added k-bit fp8 map.
|
2022-11-06 11:59:37 -08:00 |
|
Tim Dettmers
|
caf1832526
|
Added k-bit linear quantization.
|
2022-11-06 11:47:54 -08:00 |
|