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

• 5403a4aeaf null dev: support offset on buffers (#11606) nimlgenandGitHub 2025-08-10 21:58:37 +03:00
• b0dab6a4cd onnx Resize OP clean up (#11603) geohotstanandGitHub 2025-08-11 02:10:39 +08:00
• 10540414cd Add Ops.CMPEQ (#10431) Sieds LyklesandGitHub 2025-08-10 13:13:16 +02:00
• f7aa1b85fe minor sort cleanups (#11602) chenyuandGitHub 2025-08-09 22:51:23 -07:00
• dfb702ef33 fix sort for small dim (#11601) chenyuandGitHub 2025-08-09 22:17:41 -07:00
• ef17af85c6 remove .float call in llama logit (#11598) chenyuandGitHub 2025-08-09 21:02:18 -07:00
• dd3d2eb36c add training llama3 test in ci (#11599) chenyuandGitHub 2025-08-09 19:35:39 -07:00
• 3e64467322 remove freqs_cis contiguous in llama (#11597) chenyuandGitHub 2025-08-09 18:11:12 -07:00
• 7338ffead0 small beautiful_mnist update (#11596) chenyuandGitHub 2025-08-09 16:51:14 -07:00
• 45baec1aab model parallel llama (#11588) chenyuandGitHub 2025-08-09 13:54:27 -07:00
• 09bc377da3 search: print runtime failures on debug (#11593) nimlgenandGitHub 2025-08-09 23:01:19 +03:00
• 14f99ff1a1 amd: doorbell_cpu_addr is not used (#11592) nimlgenandGitHub 2025-08-09 20:03:21 +03:00
• 01c770c77b Fix z3 float cast in indexing (#11590) Sieds LyklesandGitHub 2025-08-09 17:59:23 +02:00
• 10d388499d Refactor optional.py (#11578) Sieds LyklesandGitHub 2025-08-09 17:35:05 +02:00
• 20e46a175c do not use disk with usb (#11119) nimlgenandGitHub 2025-08-09 11:58:02 +03:00
• 53179953fc viz: factor out memory graph render (#11586) qazalandGitHub 2025-08-09 01:18:11 +08:00
• 8ce72d3fad simpler disassembly table spec (#11583) qazalandGitHub 2025-08-08 22:59:26 +08:00
• 44a222a9b2 viz: move resource usage summary to server (#11582) qazalandGitHub 2025-08-08 22:08:28 +08:00
• 793ace530e update amd_uop_matmul.py import (#11581) qazalandGitHub 2025-08-08 22:07:35 +08:00
• b232c60def benchmark openpilot 0.9.9 (#11575) chenyuandGitHub 2025-08-07 22:26:14 -07:00
• 16f0edbe90 pass opts arg in get_program process replay [pr] (#11571) qazalandGitHub 2025-08-08 08:05:09 +08:00
• 960cc6533a pass through name function args in track_rewrites (#11572) qazalandGitHub 2025-08-08 07:28:52 +08:00
• 1826004ef9 feat: add tinyos builder link (#11570) wozeparrotandGitHub 2025-08-07 17:42:18 -04:00
• 82be8abfd2 move opt under codegen (#11569) George HotzandGitHub 2025-08-07 14:19:17 -07:00
• 702e38dc19 remove FUSE_ARANGE_UINT (#11567) chenyuandGitHub 2025-08-07 13:49:06 -07:00
• 6ed2dfd187 delete the arange dim mismatch restriction (#11568) George HotzandGitHub 2025-08-07 13:46:17 -07:00
• 7ae4335127 feat: generate blend index (#11566) wozeparrotandGitHub 2025-08-07 14:20:28 -04:00
• 594cbdc66f skip AM ResNet50 benchmark (#11565) chenyuandGitHub 2025-08-07 11:07:01 -07:00
• aa1a6f2132 support threshold in Tensor.softplus (#11564) chenyuandGitHub 2025-08-07 10:43:18 -07:00
• 7ee3770961 FUSE_ARANGE=1 (#11427) 3 people 2025-08-07 10:32:34 -07:00
• 4dfcfb1ae5 Revert "Revert "viz: align-center checkbox (#11555)"" geohot 2025-08-07 08:15:57 -07:00
• 7e42427a7b Revert "Revert "viz: remove color for unbind step (#11554)"" geohot 2025-08-07 08:15:51 -07:00
• dc765fbeb7 Revert "viz: timeline perf (#11533)" geohot 2025-08-07 08:08:51 -07:00
• 5650c7b86c Revert "viz: remove color for unbind step (#11554)" geohot 2025-08-07 08:08:50 -07:00
• c52facfd29 Revert "viz: align-center checkbox (#11555)" geohot 2025-08-07 08:08:50 -07:00
• 974cfbe76d Revert "viz: add support for colored tooltip text (#11556)" geohot 2025-08-07 08:08:49 -07:00
• 3bf0db80ef Revert "viz: pick the largest rect for proxy fillColor (#11558)" geohot 2025-08-07 08:08:48 -07:00
• 9764c6cdee fix mismatch reduce, try 2 (#11560) George HotzandGitHub 2025-08-07 07:57:58 -07:00
• 76079bc7f2 viz: pick the largest rect for proxy fillColor (#11558) qazalandGitHub 2025-08-07 21:40:17 +08:00
• 4f29a2c441 fix flaky test on macos (#11557) nimlgenandGitHub 2025-08-07 15:55:35 +03:00
• b3f7ea6f93 viz: add support for colored tooltip text (#11556) qazalandGitHub 2025-08-07 20:04:43 +08:00
• 91ec093464 viz: align-center checkbox (#11555) qazalandGitHub 2025-08-07 19:22:02 +08:00
• 1e205775bd viz: remove color for unbind step (#11554) qazalandGitHub 2025-08-07 19:16:21 +08:00
• 031f26632b viz: timeline perf (#11533) nimlgenandGitHub 2025-08-07 13:16:17 +03:00
• a1aa5670aa Revert "fix mismatch reduce (#11547)" (#11549) George HotzandGitHub 2025-08-06 22:43:15 -07:00
• 49d21a9055 fix mismatch reduce (#11547) George HotzandGitHub 2025-08-06 21:12:51 -07:00
• 21570545d3 move view pushing to codegen, try 2 (#11534) George HotzandGitHub 2025-08-06 15:58:38 -07:00
• 2d5bdc939d faster llama3 dataloader (#11540) wozeparrotandGitHub 2025-08-06 15:25:57 -07:00
• 80d9cced07 more test cleanups (#11544) George HotzandGitHub 2025-08-06 15:05:21 -07:00
• 6fd1332763 update some tests for less Kernel (#11543) George HotzandGitHub 2025-08-06 14:19:59 -07:00
• 09dc7af8e9 move bind to big graph (#11539) George HotzandGitHub 2025-08-06 13:27:51 -07:00
• 7c5e115747 test_mismatch_reduce (#11538) George HotzandGitHub 2025-08-06 10:02:14 -07:00
• 4fe11725c6 pass through sink arg, update linearizer test (#11536) George HotzandGitHub 2025-08-06 09:48:48 -07:00
• bfebb5c37b do store in the replace_buffers (#11535) George HotzandGitHub 2025-08-06 08:42:45 -07:00
• 1163292759 move onnx_parser into onnx (#11530) geohotstanandGitHub 2025-08-06 22:46:27 +08:00
• 7b16fadd87 load view late + simpler rewrite (#11525) George HotzandGitHub 2025-08-06 06:55:11 -07:00
• 930d8dae0c hcq: lazy prof signal allocation (#11531) nimlgenandGitHub 2025-08-06 15:28:11 +03:00
• eafc7fda12 upd perfetto (#11528) nimlgenandGitHub 2025-08-06 14:00:34 +03:00
• 1afb290027 ci: fix runner in nv (#11527) nimlgenandGitHub 2025-08-06 10:38:04 +03:00
• 61dae0685c viz: show total mem in tooltip (#11526) qazalandGitHub 2025-08-06 11:51:26 +08:00
• cf66df0ea6 put load early to make pointers match (#11524) George HotzandGitHub 2025-08-05 20:04:32 -07:00
• 92175626e3 prereqs: move views to codegen (#11522) George HotzandGitHub 2025-08-05 19:27:58 -07:00
• c9225d22ce only disable flaky test_jit_multidev_xfer (#11523) chenyuandGitHub 2025-08-05 19:17:25 -07:00
• f58fd3143d cleanup fix_kernel (#11520) George HotzandGitHub 2025-08-05 18:38:43 -07:00
• 067daee5be pin torch to 2.7.1 (#11519) George HotzandGitHub 2025-08-05 15:58:57 -07:00
• b39f43c46a optimize in rewrite, try 2 (#11518) George HotzandGitHub 2025-08-05 15:52:53 -07:00
• 07b0df0d86 hotfix: test tensor dims start at 1 geohot 2025-08-05 15:40:24 -07:00
• 4dabdf7c6d Revert "optimize in rewrite (#11516)" (#11517) George HotzandGitHub 2025-08-05 15:39:07 -07:00
• 3b777a9e05 optimize in rewrite (#11516) George HotzandGitHub 2025-08-05 15:33:26 -07:00
• ec676eddfa nv: move base address higher (#11514) nimlgenandGitHub 2025-08-05 22:42:53 +03:00
• 7703f8b805 viz: skip flops info if estimates is symbolic (#11513) qazalandGitHub 2025-08-06 03:12:52 +08:00
• fc4e713d1c jit graph split tests (#11507) nimlgenandGitHub 2025-08-05 21:32:37 +03:00
• c57fde51f9 move swizzler to opt (#11509) George HotzandGitHub 2025-08-05 11:31:30 -07:00
• ace8e9a706 fix test_conv2d_winograd (#11511) chenyuandGitHub 2025-08-05 09:15:46 -07:00
• 223aaa0492 clean up more conv tests (#11510) chenyuandGitHub 2025-08-05 09:15:30 -07:00
• 76e62a1c23 extract conv layer test logic (#11488) Garret CastroandGitHub 2025-08-05 08:15:54 -07:00
• 8b8bd6c534 make einsum generate same kernels (#11508) 3 people 2025-08-05 23:12:52 +08:00
• 011ef8fa9d Fix incorrect jit current batch devs reset (#11505) uuuvnandGitHub 2025-08-05 05:16:16 +00:00
• f02720ca2d fix fuse gate_contiguous unique (#11504) chenyuandGitHub 2025-08-04 20:43:31 -07:00
• 7f6acfb0d5 give define global and friends a shape (#11502) George HotzandGitHub 2025-08-04 19:09:39 -07:00
• 83385e7abc update gradient src in ramp.py (#11499) chenyuandGitHub 2025-08-04 15:58:03 -07:00
• 846a2826ab viz: remove TracingKey.fmt (#11482) qazalandGitHub 2025-08-05 05:00:03 +08:00
• 01d44e8f16 tiny reduce_gradient cleanup [pr] (#11498) chenyuandGitHub 2025-08-04 13:12:53 -07:00
• 8a11af01ed remove broken paperswithcode links in doc (#11497) chenyuandGitHub 2025-08-04 10:12:33 -07:00
• 4f0ee4e982 BPE tokenizer (#11415) 3 people 2025-08-04 18:52:38 +02:00
• 06af9f9236 fix double exception + add name,loc in error msg (#11487) 3 people 2025-08-04 18:41:23 +08:00
• 4877aa965a ast seems to probe nv as well (#11494) nimlgenandGitHub 2025-08-04 11:47:07 +03:00
• e0106b6b25 1/(x*c) -> (1/c)*(1/x) (#11491) chenyuandGitHub 2025-08-03 20:35:46 -07:00
• 5870352fe1 viz: factorize llvm-mca call (#11490) qazalandGitHub 2025-08-04 05:31:23 +08:00
• dbc7807c61 enable WEBGPU tests with buffer limit (#11489) chenyuandGitHub 2025-08-03 13:02:44 -07:00
• 8f374ee1f7 nv: print devfmr in gsp logs (#11484) nimlgenandGitHub 2025-08-03 15:12:53 +03:00
• 823f1a01db move cast around expand backward to tensor.py (#11483) chenyuandGitHub 2025-08-02 20:03:54 -07:00
• 0ce0f51010 generic double cast folding (#11481) chenyuandGitHub 2025-08-02 16:26:37 -07:00
• 72e0d1d0dc viz: profile the compiler in TINY device (#11457) qazalandGitHub 2025-08-03 07:03:20 +08:00
• 66be747908 few more dtype cast convinience methods (#11480) chenyuandGitHub 2025-08-02 12:47:09 -07:00
• e22e5da9a5 move some test_dtype tests to unit (#11479) chenyuandGitHub 2025-08-02 12:25:00 -07:00
• da0b955be4 hcq: cpu can be graphed (#11474) nimlgenandGitHub 2025-08-02 21:01:19 +03:00
• f7965f85aa Revert "feat: faster index building (#11462)" (#11478) chenyuandGitHub 2025-08-02 09:50:48 -07:00
• ef7e01cadf Fix SVD shape bug + Fix batched SVD bug (#11477) kevvzandGitHub 2025-08-02 09:47:41 -07:00
• 6ecaf8e7b2 refactor: use less index and simplify reduce axes check [pr] (#11476) 3 people 2025-08-03 00:44:51 +08:00