Commit Graph

Select branches

Hide Pull Requests

geohot/updates

gh-pages

master

remove_anchors

#1

#2

#3

v0.10.0

v0.10.1

v0.10.2

v0.10.3

v0.11.0

v0.12.0

v0.13.0

v0.4.0

v0.5.0

v0.6.0

v0.7.0

v0.8.0

v0.9.0

v0.9.1

v0.9.2

Mono Color

• 85591bd1ae no need for functools here (#6303) Roelof van DijkandGitHub 2024-08-28 10:19:57 +02:00
• b1e5343133 nv better error msg for p2p failure (#6301) nimlgenandGitHub 2024-08-28 01:40:45 +03:00
• ac303146ca nv sure qmd addr less than 40bits (#6288) nimlgenandGitHub 2024-08-27 20:47:38 +03:00
• 5ed6c6ef3e hotfix: 220V 15A -> 220V 20A geohot 2024-08-27 10:20:43 -07:00
• ec34d9ee36 start benchmarking ast graph rewrite (#6297) qazalandGitHub 2024-08-27 23:18:44 +08:00
• 552fbd5527 update llm.c with UOp ast [run_process_replay] (#6296) qazalandGitHub 2024-08-27 20:04:54 +08:00
• 211bfb6d8a fixed batched clip computation (#6292) Tobias FischerandGitHub 2024-08-26 20:48:15 -04:00
• 3918f6eea0 refactor amd render_kernel (#6223) 3 people 2024-08-26 13:28:36 -03:00
• 3132449086 refactor _make_{cuda/clang}_dtype into render_vector_prefix (#6287) ignaciosicaandGitHub 2024-08-26 13:14:44 -03:00
• ab2714423b Add einsum tests (#6286) 3 people 2024-08-26 18:09:25 +02:00
• b76f0c875e lazy const fold idiv 1 (#6285) chenyuandGitHub 2024-08-26 10:29:59 -04:00
• af7c04ff57 Tensor.__floordiv__ (#6283) chenyuandGitHub 2024-08-26 09:43:40 -04:00
• d2f8eeed2e make [compare_schedule] the default [run_process_replay] (#6273) qazalandGitHub 2024-08-26 21:40:03 +08:00
• 067aeaeb2f single arange fusion with graph rewrite (#6160) qazalandGitHub 2024-08-26 18:18:16 +08:00
• b4381e9777 uop output_st is Optional [run_process_replay] (#6282) qazalandGitHub 2024-08-26 17:58:55 +08:00
• 1c0456af89 add UOps.SWIZZLE (#6271) qazalandGitHub 2024-08-26 16:08:51 +08:00
• 002f60b4c3 fix intel wmma flop counting, add flop counting tests for different tensor cores (#6192) CaltropHungertonandGitHub 2024-08-25 20:37:05 -05:00
• 331b0f5477 new clip gather (#6277) Tobias FischerandGitHub 2024-08-25 19:27:24 -04:00
• f0cc8ca5f2 generic st_fixup in scheduler graph rewrite [compare_schedule] (#6278) qazalandGitHub 2024-08-25 16:02:17 +08:00
• 70015bd89c move permute_reduces to uop movementops [run_process_replay] (#6272) qazalandGitHub 2024-08-25 15:25:51 +08:00
• b86907c6c7 UOp.const(x.dtype, y) -> x.const(y) [run_process_replay] (#6276) chenyuandGitHub 2024-08-24 21:39:50 -04:00
• 00282afa41 identity element of binary ops (#6275) chenyuandGitHub 2024-08-24 18:10:19 -04:00
• ee245b48a9 refactor reduceop swizzling (prep for UOps.SWIZZLE) [compare_schedule] (#6269) qazalandGitHub 2024-08-24 23:17:19 +08:00
• 3cf507ae7f remove extra.ops and LazyOp support from Kernel (#6267) gswanggandGitHub 2024-08-24 06:44:38 -07:00
• ccb05d8baa fixup neg tests [run_process_replay] (#6268) qazalandGitHub 2024-08-24 21:35:43 +08:00
• ea76b93814 migrate test_linearizer_dumb.py to UOp AST (#6241) gswanggandGitHub 2024-08-24 06:27:29 -07:00
• e44653e25a migrate test_linearizer_failures.py to UOp AST (#6240) 3 people 2024-08-24 06:26:58 -07:00
• 1b4ad982e5 share REDUCE_ALU in multi and schedule [run_process_replay] (#6266) qazalandGitHub 2024-08-24 21:16:38 +08:00
• 1dc6040877 migrate test_search.py to UOp AST (#6245) 3 people 2024-08-24 06:13:53 -07:00
• ae23540d6e refresh process replay schedule ref in reset.py (#6265) qazalandGitHub 2024-08-24 21:12:51 +08:00
• 7be5eede71 migrate test_linearizer_overflows.py to UOp AST (#6244) gswanggandGitHub 2024-08-24 06:10:29 -07:00
• 943ab97d24 fix Tensor.prod for multitensor (#6264) chenyuandGitHub 2024-08-24 08:52:24 -04:00
• bcb2f1caa3 init REDUCE_AXIS with BinaryOps (#6256) qazalandGitHub 2024-08-24 16:28:41 +08:00
• da5cf11859 fix acc init value for MUL (#6263) chenyuandGitHub 2024-08-23 23:19:44 -04:00
• a7bf20c7cd feat: updated tinybox docs (#6261) wozeparrotandGitHub 2024-08-23 18:27:46 -07:00
• 26498b322e add BEAM to external_benchmark_schedule.py geohot 2024-08-23 18:10:46 -07:00
• 53a73038e3 hotfix: TestGraphRewriteEfficiency.test_create_many_uops geohot 2024-08-23 15:51:57 -07:00
• 7c3ba3fa8a improve match stats + custom early reject [run_process_replay] (#6260) George HotzandGitHub 2024-08-23 15:28:57 -07:00
• 0b0a8829fb allowed_len early stop [run_process_replay] (#6257) George HotzandGitHub 2024-08-23 13:31:07 -07:00
• a18744188f more early reject [run_process_replay] (#6254) George HotzandGitHub 2024-08-23 12:16:44 -07:00
• 0d4887e9df use UOps.WMMA everywhere (#6255) qazalandGitHub 2024-08-24 03:03:26 +08:00
• 66d0b14a20 simpler CMPLT UOp _min_max [run_process_replay] (#6251) chenyuandGitHub 2024-08-23 10:36:16 -04:00
• 590c0922b6 Tensor.prod (#6250) chenyuandGitHub 2024-08-23 10:06:32 -04:00
• 78d6bd8b41 start graph rewrite in the scheduler (#6248) qazalandGitHub 2024-08-23 18:15:55 +08:00
• 75700edf73 minor bitcast touchup (#6246) chenyuandGitHub 2024-08-22 20:25:28 -04:00
• 4d40de867b remove redundant c1-(x+c2) rule [run_process_replay] (#6243) chenyuandGitHub 2024-08-22 16:45:49 -04:00
• 238896ca02 loooking into graph rewrite speed (#6239) George HotzandGitHub 2024-08-22 13:17:55 -07:00
• f62c4b3b5f remove redundant -(x*c) pattern [run_process_replay] (#6242) chenyuandGitHub 2024-08-22 16:11:02 -04:00
• e745e16441 remove UnaryOps.NEG (#6238) chenyuandGitHub 2024-08-22 14:21:39 -04:00
• 6c4ddd6260 hcq skip tests when no multidev (#6235) nimlgenandGitHub 2024-08-22 18:27:16 +03:00
• 08539f08b0 fix UOp repr with Variable in arg (#6236) chenyuandGitHub 2024-08-22 11:06:33 -04:00
• 3fc8203475 remove NEG from handwritten ast in tests (#6234) chenyuandGitHub 2024-08-22 09:06:59 -04:00
• 1c5ef5b793 format test_linearizer_failure (#6231) chenyuandGitHub 2024-08-21 21:10:56 -04:00
• 5cdec79469 simpler expand without dont_expand_args [run_process_replay] (#6230) George HotzandGitHub 2024-08-21 17:48:45 -07:00
• 78c94abe9c raise time limit for ci in test_profile_multidev_transfer (#6227) nimlgenandGitHub 2024-08-21 22:42:03 +03:00
• c74b318458 migrate test_linearizer.py to UOp AST, pt. 2 (#6228) gswanggandGitHub 2024-08-21 15:16:11 -04:00
• c3168952f0 wip: tracking pattern matcher [run_process_replay] (#6225) George HotzandGitHub 2024-08-21 11:57:26 -07:00
• a666450e4d UOp pattern x + x -> x * 2 (#6224) chenyuandGitHub 2024-08-21 12:06:19 -04:00
• c9a9631818 no UnaryOps.NEG in generated UOp patterns (#6209) chenyuandGitHub 2024-08-21 11:08:22 -04:00
• 3b8cc5a3e0 more multireduce tests prep for neg removal [run_process_replay] (#6220) qazalandGitHub 2024-08-21 17:45:24 +08:00
• 86c036f0d3 reorder uops.py [run_process_replay] (#6219) qazalandGitHub 2024-08-21 16:39:55 +08:00
• f03e5a4b3b test_multireduce const has a shape (#6218) qazalandGitHub 2024-08-21 16:02:45 +08:00
• 911bf7216c remove unused match rules [run_process_replay] (#6217) George HotzandGitHub 2024-08-21 00:16:04 -07:00
• 2c42e9c2c6 faster rewrite, no folder in expand/reduce [run_process_replay] (#6216) George HotzandGitHub 2024-08-20 23:36:58 -07:00
• 16f420f7a7 split full_graph_rewrite and linearize_uop [run_process_replay] (#6215) George HotzandGitHub 2024-08-20 20:12:33 -07:00
• 9faf205601 CIFAR trainer + various bugfixes / improvements (#6146) George HotzandGitHub 2024-08-20 16:58:46 -07:00
• 296368f0dd Revert "delete arg from cast [run_process_replay] (#6202)" (#6214) George HotzandGitHub 2024-08-20 16:45:30 -07:00
• 89c4cffd86 nv fix size in SET_SEMAPHORE_A (#6213) nimlgenandGitHub 2024-08-21 01:47:10 +03:00
• ec52a09393 delete arg from cast [run_process_replay] (#6202) qazalandGitHub 2024-08-21 05:06:16 +08:00
• 7376b67e36 extra/gemm/triton_nv_matmul: fix Program arguments (#6212) Francis LamandGitHub 2024-08-20 14:05:38 -07:00
• 4bb98d8882 Fix track_running_stats in batchnorm (#6200) madt2709andGitHub 2024-08-20 14:01:22 -07:00
• d9c62a33c3 add cifar to datasets.py (#6210) George HotzandGitHub 2024-08-20 11:42:49 -07:00
• a5d79688db fix indexing out of bounds (#6208) George HotzandGitHub 2024-08-20 11:34:56 -07:00
• 4451bcaf95 update test_arange test_llama_embedding_opt (#6207) chenyuandGitHub 2024-08-20 13:58:43 -04:00
• e4bb63c1be Refactor amd kernel prefix (#6205) ignaciosicaandGitHub 2024-08-20 14:37:36 -03:00
• 074cf780dd add option to only benchmark schedule [run_process_replay] (#6204) qazalandGitHub 2024-08-20 21:51:27 +08:00
• 8fd8b970b0 update URL to eval cases from recent MLPerf file movements (#6201) Francis LataandGitHub 2024-08-20 08:43:13 -04:00
• 0e6f057eae migrate test_linearizer.py to UOP AST (pt. 1) (#6150) 3 people 2024-08-20 03:02:20 -04:00
• 10330a41c7 add CMPNE tests in test_uops (#6196) chenyuandGitHub 2024-08-19 19:41:21 -04:00
• 21d6739237 remove UnaryOps.NEG from lazy.py (#6193) chenyuandGitHub 2024-08-19 18:41:28 -04:00
• 4d1b5781b5 remove UnaryOps.NEG from function.py (#6187) chenyuandGitHub 2024-08-19 17:39:15 -04:00
• bc44e6501b _gpu_alloc -> allocator.alloc (#6189) nimlgenandGitHub 2024-08-19 23:34:22 +03:00
• 96d502d8b7 update function.Max backward (#6190) chenyuandGitHub 2024-08-19 16:06:14 -04:00
• bdd6325f31 default num_classes value for one_hot (#6182) Gabe CaldwellandGitHub 2024-08-19 15:07:14 -04:00
• 9328248610 support for std_mean and cross_entropy (#6181) Alessandro BenettiandGitHub 2024-08-19 12:06:44 -07:00
• 53b20afa3f Write tar_extract (#6180) 3 people 2024-08-19 21:06:17 +02:00
• 8556d0c642 Support gunzip in fetch (#6176) Eitan TurokandGitHub 2024-08-19 15:04:40 -04:00
• 705b8066ab function.Div -> function.IDiv [run_process_replay] (#6188) chenyuandGitHub 2024-08-19 14:59:41 -04:00
• ee5fe12630 disallow some uops at different levels [run_process_replay] (#6186) qazalandGitHub 2024-08-20 02:23:44 +08:00
• 5d742f7fe3 Missing features from rearrange (#6184) samm393andGitHub 2024-08-19 19:19:07 +01:00
• 2242ff84be type verify intermediate UOps [run_process_replay] (#6140) qazalandGitHub 2024-08-20 01:59:01 +08:00
• 478145cb8e lowering error in diff_schedule is fine [run_process_replay] (#6185) qazalandGitHub 2024-08-20 01:51:12 +08:00
• 00578a021b re:6125 switch real_size to use uops [run_process_replay] (#6138) 3 people 2024-08-19 13:20:24 -04:00
• e28d29641f more scheduler process replay tooling [run_process_replay] (#6178) qazalandGitHub 2024-08-19 20:35:51 +08:00
• b36a7273c6 RUF018 assignment-in-assert [run_process_replay] (#6172) chenyuandGitHub 2024-08-19 00:34:52 -04:00
• 9c60a27ece lower float64 sin fuzzer threshold (#6173) chenyuandGitHub 2024-08-19 00:25:42 -04:00
• fd7c84c1c8 Rearrange (#6106) samm393andGitHub 2024-08-19 04:22:28 +01:00
• 2de174677a threefry touchup [run_process_replay] (#6169) chenyuandGitHub 2024-08-18 23:01:24 -04:00
• 724e408736 add support for retain_graph in backward (#6145) David González MartínezandGitHub 2024-08-19 01:08:31 +02:00
• 0c5189de25 threefry half (#6154) wozeparrotandGitHub 2024-08-18 15:23:12 -07:00