214 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
broncotc	2dcf38289d	should be hippified, and all cuda checkes cleaned up, makefile not updated yet	2022-11-23 17:52:19 -08:00
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
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
Tim Dettmers	1efb87d89d	Added FP8 quantization map.	2022-11-03 19:49:50 -07:00
Tim Dettmers	8d87c0b852	Fixed CUDA setup bugs, including #81.	2022-10-31 18:04:49 -07:00
Tim Dettmers	4844aef4ff	Fixing bad error when GPU was not detected for #73.	2022-10-27 08:54:30 -07:00
Tim Dettmers	96ab2af1ef	Bump version.	2022-10-27 07:09:08 -07:00
Tim Dettmers	29e239e4d1	Merge pull request #72 from tomaarsen/hotfix/uncalled_func ... Prevent `AttributeError: 'function' object has no attribute 'add_log_entry'` on logging	2022-10-27 07:06:54 -07:00
Tom Aarsen	4faf6cb7e9	Replace seemingly incorrect use of CUDA_RUNTIME_LIB	2022-10-26 09:43:57 +02:00
Tom Aarsen	c584482f1f	Resolve cases of CUDASetup.get_instance not being called when used	2022-10-26 09:37:16 +02:00
Tim Dettmers	a371be302d	Added CUDA SETUP instruction generator.	2022-10-25 08:01:19 -07:00
Tim Dettmers	62e1649357	Bumped version. Fixes for diverse issues relating CUDA SETUP.	2022-10-24 14:47:56 -07:00
Tim Dettmers	df86625a93	Isolated CUDASetup logging; all tests green.	2022-10-24 11:54:25 -07:00
Tim Dettmers	b844e104b7	Updated docs (#32) and changelog.	2022-10-09 19:31:43 -07:00
Tim Dettmers	62b6a9399d	Added CUDA 11.8 install and deployment.	2022-10-09 19:02:28 -07:00
Tim Dettmers	ed2e3b9db4	Merge pull request #36 from tomaarsen/hotfix/os_error_name_too_long ... Fixes `OSError: File name too long` when environment variable is too long	2022-10-09 16:47:11 -07:00
Tim Dettmers	76699b4a8d	Merge pull request #37 from tomaarsen/hotfix/colab_just_cpu ... Perform check using implicit list length	2022-10-09 16:43:58 -07:00
Tim Dettmers	7740c6e9c9	Fixed url in setup.py (#38), updated changelog.	2022-09-19 21:13:40 -07:00
Tim Dettmers	439f2b0c10	Merge pull request #33 from dbaranchuk/memory-efficient-backward ... Memory efficient backward	2022-09-19 21:09:25 -07:00
justheuristic	76ce9aa6da	try fp32	2022-09-20 06:51:25 +03:00
Tim Dettmers	292a478716	set threshold	2022-09-20 06:42:05 +03:00
justheuristic	a07825ac31	review	2022-09-20 06:40:36 +03:00
Tim Dettmers	9b7d307b8c	review	2022-09-20 06:36:32 +03:00
justheuristic	cff3a71599	cast device	2022-09-18 01:26:25 +03:00
justheuristic	32a9a88f98	cast device	2022-09-18 01:26:12 +03:00
justheuristic	01b4c6a048	cast device	2022-09-18 01:25:56 +03:00
justheuristic	e4086a2758	cast device	2022-09-18 01:24:57 +03:00
justheuristic	725cc72993	cast device	2022-09-18 01:24:44 +03:00
justheuristic	28a9313ddc	cast before allclose	2022-09-18 01:24:27 +03:00
justheuristic	95dafc6475	cast before allclose	2022-09-18 01:22:31 +03:00
justheuristic	37f805bb44	debug	2022-09-18 01:21:12 +03:00
justheuristic	6a826c41a6	pre-cast	2022-09-18 01:20:34 +03:00
justheuristic	d9b8789818	debug	2022-09-18 01:13:58 +03:00
justheuristic	5d65817101	debug	2022-09-18 01:09:24 +03:00
justheuristic	4da2227fcb	debug	2022-09-18 01:03:21 +03:00
justheuristic	4b4a9effd1	debugprint	2022-09-18 01:02:13 +03:00
justheuristic	7906dc4c9a	debugpritn	2022-09-18 00:57:26 +03:00
justheuristic	2cd047e35d	run backward	2022-09-18 00:55:53 +03:00
justheuristic	591f60395a	add memory efficient backward	2022-09-18 00:52:53 +03:00
justheuristic	579b8c782f	reduce diff	2022-09-18 00:47:58 +03:00
justheuristic	76ece2c126	rollback	2022-09-18 00:43:56 +03:00
justheuristic	18f142e268	addmm_	2022-09-18 00:43:02 +03:00
justheuristic	f6670329fb	bump threshold to 0.21	2022-09-18 00:42:23 +03:00