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

• d82370f6ef docs: fix broken links and update is_floating_point (#6023) chenyuandGitHub 2024-08-10 15:58:48 -04:00
• d58ae17771 Cleanup cstlye render_const [run_process_replay] (#6024) gswanggandGitHub 2024-08-10 15:58:02 -04:00
• 10374a2741 relax rtol for test_arange_fuse_grouped_children (#6026) chenyuandGitHub 2024-08-10 15:49:11 -04:00
• cf7d3c1eb8 fix tests locally on metal (#6025) George HotzandGitHub 2024-08-10 12:36:22 -07:00
• e6c7c3e499 update pylint path to check indent/space for all (#6022) chenyuandGitHub 2024-08-10 14:41:09 -04:00
• cfb04c67d1 run unit tests separate from others (and only once) (#6020) George HotzandGitHub 2024-08-10 11:17:56 -07:00
• 8302dd6ea4 remove noqa: E501 from transcendental geohot 2024-08-10 10:30:05 -07:00
• 350276e947 simpler device_from_env [run_process_replay] (#6015) chenyuandGitHub 2024-08-10 13:17:46 -04:00
• ee3b015407 ELF loader strtab fix and tests (#6011) uuuvnandGitHub 2024-08-10 20:13:16 +03:00
• 54e176fb4f Ignore non-computational backends when overwriting the default (#5770) Jun ZhangandGitHub 2024-08-11 00:23:29 +08:00
• 3ef2788c4f hotfix: run the entire test_conv_bw schedule (#6014) qazalandGitHub 2024-08-10 22:55:41 +08:00
• 0e62076cf5 more process replay cleanups (#6013) qazalandGitHub 2024-08-10 22:29:10 +08:00
• 266afad8ed hotfix: skip schedule capture in benchmarks (#6012) qazalandGitHub 2024-08-10 22:13:53 +08:00
• 63a8bc29d4 addition divisor in UOp div_folding (#6002) chenyuandGitHub 2024-08-09 20:09:05 -04:00
• 52a74e1d6f recursive div_folding to simplify logic (#6008) chenyuandGitHub 2024-08-09 19:23:06 -04:00
• a4ec4e890a merge mul div pattern into div_folding (#6006) chenyuandGitHub 2024-08-09 18:49:36 -04:00
• 5961faa4be minor change to UOp div_fold (#6004) chenyuandGitHub 2024-08-09 17:09:59 -04:00
• 7373b05ee8 assert conv bw reduceops merge [compare_schedule] (#6001) qazalandGitHub 2024-08-10 00:29:56 +08:00
• b67d521a07 assert test_conv_bw correctness (#6000) qazalandGitHub 2024-08-09 23:30:36 +08:00
• ce066fd754 nv do not recalc mv_address (#5998) nimlgenandGitHub 2024-08-09 17:16:34 +03:00
• a833f1a735 scheduler process replay with [compare_schedule] (#5997) qazalandGitHub 2024-08-09 21:58:22 +08:00
• 24c7c41ce0 diff LazyBuffer schedules in process replay (#5996) qazalandGitHub 2024-08-09 19:16:43 +08:00
• d269bc95fa faster tinychat (#5993) wozeparrotandGitHub 2024-08-08 19:16:26 -07:00
• 1f1eb46af6 more failed simplified UOp div test case (#5992) chenyuandGitHub 2024-08-08 18:39:25 -04:00
• 94dc61aa1f typeguard fixes for beautiful-mnsit JIT=2 METAL=1 [run_process_replay] (#5984) gswanggandGitHub 2024-08-08 14:53:33 -07:00
• c3e1ae2535 add failed simplified UOp div test case (#5990) chenyuandGitHub 2024-08-08 17:37:48 -04:00
• 38d5eecc68 hcq profiler support args (#5989) nimlgenandGitHub 2024-08-09 00:18:36 +03:00
• 45b1761175 smaller test_llama_embedding + assert correctness (#5986) qazalandGitHub 2024-08-09 03:11:29 +08:00
• 8c99bdab08 More Multireduce Tests (#5968) TimmyandGitHub 2024-08-08 12:04:08 -07:00
• 3c0924cac4 UOp int alu patterns match all int (#5987) chenyuandGitHub 2024-08-08 14:50:58 -04:00
• df44a4e861 Make vectorization of CONST explicit (#5322) 4 people 2024-08-08 10:59:05 -07:00
• 62c77a2831 trim const in UOp div_folding (#5982) chenyuandGitHub 2024-08-08 12:49:05 -04:00
• e6d41b0ce7 hotfix: adjust test_backward_pass_diamond_model thresholds (#5981) qazalandGitHub 2024-08-09 00:20:53 +08:00
• 08d22066ee simplify ALU vmin==vmax fold (#5962) gswanggandGitHub 2024-08-08 08:29:16 -07:00
• c9b4602854 no load in INITMLPERF (#5957) Elias WahlandGitHub 2024-08-08 17:28:24 +02:00
• 183c4c91a3 fix non-jitted transfers in profile (#5980) nimlgenandGitHub 2024-08-08 17:58:08 +03:00
• 76eca0d27e nv fix host mem mappings (#5979) nimlgenandGitHub 2024-08-08 17:03:44 +03:00
• e89eff11a6 amd raise when not supported arch (#5978) nimlgenandGitHub 2024-08-08 14:46:14 +03:00
• bc55c8a30e pmatmul example + GB/s bugfix [run_process_replay] (#5974) George HotzandGitHub 2024-08-07 22:32:11 -07:00
• c5baa3d66b hotfix: don't run OOM test in CI geohot 2024-08-07 22:19:29 -07:00
• 859d0e4709 UOp simplify (x+c0)*c1 -> x*c1+c0*c1 (#5973) chenyuandGitHub 2024-08-07 21:25:22 -04:00
• 97d708252a remove realize from threefry (#5969) wozeparrotandGitHub 2024-08-07 15:08:49 -07:00
• bf8ec23b00 hotfix: contiguous on precompute_freqs_cis geohot 2024-08-07 14:40:04 -07:00
• d3e427c8d9 fix sqlite3 locks (#5971) wozeparrotandGitHub 2024-08-07 14:38:19 -07:00
• cc37c99ae4 tiny hcq touchups (#5964) nimlgenandGitHub 2024-08-07 21:03:20 +03:00
• 8d8704af2d fix amd exec_update for locals (#5966) nimlgenandGitHub 2024-08-07 21:02:56 +03:00
• 0ddcd005f5 fix priority width and give more space for src (#5509) ignaciosicaandGitHub 2024-08-07 14:48:18 -03:00
• 0c4e9dbe71 retrieve defined opencl error codes (#5792) tyoc213andGitHub 2024-08-07 11:46:24 -06:00
• 4b48f166ec Refactor render_kernel for NV [run_process_replay] (#5965) 3 people 2024-08-07 14:36:04 -03:00
• d6f4a61c42 graph LBScheduleItem [run_process_replay] (#5960) qazalandGitHub 2024-08-08 00:59:11 +08:00
• 0a8668cf30 improvements to docs geohot 2024-08-07 09:57:24 -07:00
• 7677361d90 test pushing through different expands in 1 kernel (#5963) qazalandGitHub 2024-08-08 00:33:18 +08:00
• 564a352194 nv unify _gpu_free (#5961) nimlgenandGitHub 2024-08-07 18:18:17 +03:00
• 39c8c9c00a Add docs (#5942) 3 people 2024-08-07 10:38:51 -04:00
• 39dda3d042 rename prescheduled items to lsi [run_process_replay] (#5959) qazalandGitHub 2024-08-07 19:31:50 +08:00
• 728b7e189e diff_schedule tests [run_process_replay] (#5958) qazalandGitHub 2024-08-07 18:50:27 +08:00
• a7163b80d8 lower test_transcendental fuzz test threshold for sin float64 (#5956) chenyuandGitHub 2024-08-07 02:04:37 -04:00
• fa3a36e576 fancier UOp div gcd folding (#5953) chenyuandGitHub 2024-08-07 02:04:25 -04:00
• aa7fd7ef74 Use (-self).lt(-x+1) for UOp.ge (#5955) chenyuandGitHub 2024-08-07 01:31:27 -04:00
• 3d445039c2 hotfix: 8800 lines for AMX+intel tc geohot 2024-08-06 17:50:26 -07:00
• 658d58784b embedding doesn't cast (#5952) George HotzandGitHub 2024-08-06 17:49:14 -07:00
• 30d0cb2a82 fix: fix transcendental flakyness on exp float with 9.96875 (#5951) wozeparrotandGitHub 2024-08-06 17:32:13 -07:00
• 3a0515ea22 hotfix: process_replay/diff_schedule.py to LBScheduleItem geohot 2024-08-06 16:59:37 -07:00
• aee737bd9e divide by gcd in UOp div folding (#5949) chenyuandGitHub 2024-08-06 20:00:57 -04:00
• 6d1fdcfce2 don't reduce the same thing in a vector (#5950) George HotzandGitHub 2024-08-06 16:59:15 -07:00
• d5d7f4e7b8 more TestIndexing correctness asserts [run_process_replay] (#5948) qazalandGitHub 2024-08-07 06:50:42 +08:00
• 7f062929e8 start all cached scheduler functions with buf, st [run_process_replay] (#5946) qazalandGitHub 2024-08-07 06:24:22 +08:00
• 794796256c UOp.const_factor [run_process_replay] (#5945) chenyuandGitHub 2024-08-06 18:18:29 -04:00
• c9862e17d4 MLPERF BERT submission scripts (#5931) Elias WahlandGitHub 2024-08-07 00:09:18 +02:00
• 73d4d51845 add LBScheduleItem type [run_process_replay] (#5944) George HotzandGitHub 2024-08-06 14:49:40 -07:00
• 1dab75ae37 clean up mlperf dataloader import (#5940) chenyuandGitHub 2024-08-06 17:10:08 -04:00
• 7b6496f2e6 fix the reduceops cache breaking beautiful_mnist (#5938) qazalandGitHub 2024-08-07 05:02:54 +08:00
• 1417cc8df1 can reenable that test now (#5914) George HotzandGitHub 2024-08-06 13:38:21 -07:00
• 75154d7ae2 add some types to the scheduler [run_process_replay] (#5941) George HotzandGitHub 2024-08-06 12:23:54 -07:00
• e077bc7baf move memory planner to realize (#5937) George HotzandGitHub 2024-08-06 10:41:29 -07:00
• 489575c3be more UOp sum div with gcd tests (#5936) chenyuandGitHub 2024-08-06 12:50:10 -04:00
• 81ae9fadc8 Float4 support for CLANG (#5915) ignaciosicaandGitHub 2024-08-06 11:50:12 -03:00
• a7db4c3ee9 show timings for DIFF_ARANGE=1 (#5935) qazalandGitHub 2024-08-06 22:20:38 +08:00
• 102a8c184b diff fused arange schedules with ARANGE_DIFF=1 (#5934) qazalandGitHub 2024-08-06 21:52:26 +08:00
• f7761245aa save_schedule pre toposort [run_process_replay] (#5933) qazalandGitHub 2024-08-06 20:10:01 +08:00
• 895e062723 nv remove useless init (#5932) nimlgenandGitHub 2024-08-06 14:41:40 +03:00
• 3d4742dd2e override output shape in fused assign (#5930) qazalandGitHub 2024-08-06 18:28:50 +08:00
• 341c394c89 amd save exec offsets (#5928) nimlgenandGitHub 2024-08-06 12:11:46 +03:00
• 5808e8a30f mockgpu remu changes (#5925) wozeparrotandGitHub 2024-08-05 19:26:58 -07:00
• 09b7722637 UOp generic div folding (#5896) chenyuandGitHub 2024-08-05 21:38:43 -04:00
• 3e1336957d test arange with all opts (#5923) George HotzandGitHub 2024-08-05 18:38:25 -07:00
• 2e7adb529f don't run kernels with 1000x more compute (fix BEAM with FUSE_ARANGE) (#5924) George HotzandGitHub 2024-08-05 16:28:09 -07:00
• 5d17f54e3c fast mnist indexing (#5921) George HotzandGitHub 2024-08-05 13:55:15 -07:00
• e81c18f494 make the arange test check correctness [run_process_replay] (#5920) George HotzandGitHub 2024-08-05 13:41:06 -07:00
• 8d1c884e78 capture the const pattern in both directions (#5919) George HotzandGitHub 2024-08-05 12:15:38 -07:00
• 42f599870c unroll arange is broken (#5918) George HotzandGitHub 2024-08-05 12:15:07 -07:00
• 6740a0a6a0 hip_ioctl changes (#5917) wozeparrotandGitHub 2024-08-05 11:58:38 -07:00
• 70949ea7e6 test cstyle compile error for max with inline const (#5838) qazalandGitHub 2024-08-06 00:02:16 +08:00
• 98df648a79 metal sync queues in transfer (#5308) nimlgenandGitHub 2024-08-05 18:43:22 +03:00
• 6a70c69167 hotfix: TC renders nv_bfloat16 (#5913) qazalandGitHub 2024-08-05 23:40:31 +08:00
• 8ce9e6e693 Fix vectorized dtype rendering bug in CLANG (#5911) P4ssengerandGitHub 2024-08-05 11:43:26 -03:00
• e0c6520138 check arange fusing with VIEW and COPY (#5912) qazalandGitHub 2024-08-05 22:09:21 +08:00
• 590b9ebb34 hcq copy queue is optional (#5909) nimlgenandGitHub 2024-08-05 14:03:25 +03:00
• 159ac06b5b remove unused reduce rules + improve unparented (#5908) George HotzandGitHub 2024-08-04 18:18:27 -07:00
• d7387d31bf remove useless reduce cases [run_process_replay] (#5907) George HotzandGitHub 2024-08-04 17:11:08 -07:00