Commit Graph

65 Commits

Author SHA1 Message Date
Tim Dettmers
5fab673442 Added fp32 compute type for gemv_4bit. 2023-07-09 21:06:01 -07:00
Tim Dettmers
4b88d69de7 Added abitrary data types; fixed a bug for small matrices. 2023-07-09 12:04:09 -07:00
Tim Dettmers
02fd80cb81 Added bfloat16 quantizations and tests. 2023-07-04 19:58:31 -07:00
Tim Dettmers
dfe6900b94 Vectorized loads, conflict free NF4; 52 vs 172. 2023-07-04 15:20:10 -07:00
Tim Dettmers
f89ff93e26 Initial 4-bit naive batch size 1, 81 vs 185. 2023-07-03 18:45:38 -07:00
Tim Dettmers
1b8772a8f3 Added PagedLion and bf16 Lion. 2023-05-23 19:37:38 -07:00
Tim Dettmers
675baa79d2 Merge remote-tracking branch 'origin/main' into merge 2023-05-07 13:34:03 -07:00
Tim Dettmers
ec38ba95b0 Added paging. 2023-05-06 11:14:06 -07:00
Tim Dettmers
264a948539 4-bit draft; 128 vector load 240. 2023-05-02 16:15:38 -07:00
Tim Dettmers
77f15fdce9 Shared memory efficient 240. 2023-05-02 11:38:11 -07:00
Tim Dettmers
f9bfea8f23 Baseline for debugging. 2023-05-02 07:24:12 -07:00
Tim Dettmers
7bfa09d0fc 8x32 240 6 warps. 2023-05-01 16:38:09 -07:00
Tim Dettmers
3d4a2eadd3 16x16 240. 2023-05-01 16:23:45 -07:00
Tim Dettmers
7cc8ff4727 Warp specalization 362. 2023-05-01 08:21:12 -07:00
Tim Dettmers
30d03e0254 64 threads, high smem, 434. 2023-04-30 18:55:12 -07:00
Tim Dettmers
604bb3fb57 Slow non-vector 530. 2023-04-30 18:06:01 -07:00
Tim Dettmers
ad07d254fb Slow tensor core solution. 2023-04-30 17:43:02 -07:00
Tim Dettmers
21723f796a 4-bit draft. 2023-04-29 21:52:47 -07:00
Tim Dettmers
cad839941b Added bit template. 2023-04-28 22:10:42 -07:00
Tim Dettmers
f3e97ccbd2 New implementation for batch size 1. 2023-04-28 21:29:40 -07:00
Tim Dettmers
f6df4aef6a Added fp16 and thread/item template. 2023-04-28 18:26:52 -07:00
Tim Dettmers
3aef78342a Added template refactor. 2023-04-28 17:34:08 -07:00
Tim Dettmers
c1bfb210c5 First baseline kernel. 2023-04-28 17:19:02 -07:00
Tim Dettmers
9cab14a3ff Adedd pipeline draft. 2023-04-27 15:12:49 -07:00
Tim Dettmers
d1c4c20568 Added non-cutlass template. 2023-04-27 15:11:26 -07:00
Tim Dettmers
0afc8e9e2f Best attempt at cutlass3. 2023-04-26 17:12:34 -07:00
Tim Dettmers
84964db937 CUTLASS compiles. 2023-04-25 17:15:51 -07:00
Tim Dettmers
6e2544da25 Added cutlass example. 2023-04-25 16:15:44 -07:00
Tim Dettmers
6bfd7a405f Initial template. 2023-04-25 16:13:43 -07:00
Tim Dettmers
7dc198feb7 Added 32-bit optimizer for bfloat16 gradients. 2023-04-17 18:01:49 -07:00
Tim Dettmers
7140c01405 Merge branch 'main' into fp8_merge 2023-04-12 11:44:39 -07:00
Tim Dettmers
64cc05920d First draft of NF4. 2023-04-02 16:10:35 -07:00
Tim Dettmers
c4cfe4fbdd Added bf16 Adam. 2023-04-01 10:33:03 -07:00
Tim Dettmers
8645d1f71c Added normal quant. 2023-03-29 18:41:37 -07:00
Tim Dettmers
69810521d3 Some small changes. 2023-03-27 09:12:57 -07:00
Phil Wang
6c377b39b6 always pass beta2 into all the 1state functions 2023-03-10 13:00:59 -08:00
Phil Wang
c99b44f774 do the epsilon beta2 switcharoo within the cuda code, and not within the python class (so that the state dict still makes sense) 2023-03-10 08:57:59 -08:00
Phil Wang
8618bed001 swap the order in which momentum and parameters are updated in ops.cu 2023-03-10 08:39:06 -08:00
Phil Wang
cb4c3c8c66 do a bunch of typical bookkeeping before getting to main lion logic 2023-03-09 10:10:19 -08:00
Tim Dettmers
2489d819c5 Added more blocksizes for stochastic rounding; fixed dequant blocksize. 2023-02-14 13:55:17 -08:00
Tim Dettmers
3ac5840c03 Added fp4 quant/dequant and dequant optimizations. 2023-02-04 14:52:04 -08:00
Tim Dettmers
c91f592ad7
Merge branch 'main' into cleanup 2023-01-02 11:19:16 +01:00
Tim Dettmers
c059bd2848 Added additional blocksizes: {64, 128, 256}. 2022-11-20 14:18:15 -08:00
Tom Aarsen
b104ce3b62
Merge branch 'main' into cleanup 2022-11-17 15:22:29 +01:00
Tim Dettmers
6bc2b992be Added blocksizes 2048, 1024, and 512 to blockwise quant. 2022-11-06 16:27:48 -08:00
Tom Aarsen
1eec77d34c Remove trailing whitespace & ensure newline at EOF 2022-10-27 13:11:29 +02:00
Tim Dettmers
ee5b947e63 Fixed issue where Pascal was not displaying proper error. 2022-08-23 16:00:26 -07:00
Tim Dettmers
a6664de072 Enhanced error handling in CUDA SETUP failures. 2022-08-16 19:03:19 -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
a4532c59f7 Removed faulty asserts. 2022-08-06 09:31:05 -07:00