branch: master
Commits on master
- bd49d28 hotfix: skip fetch tests always 1 year ago
- b683d0f hotfix: 100% accuracy is wrong 1 year ago
- 8bcf533 gitignore open-images-v6TEST 1 year ago
- ea06f65 fusion tests from test_opt (#4357) 1 year ago
- 995d264 hotfix: add CNAME to put docs at docs.tinygrad.org 1 year ago
- 683b7c6 pad first batch of imagenet dataloader and update eval (#4368) 1 year ago
- 4a26718 feat: tinyboxgreen (#4365) 1 year ago
- 16838ea mlperf/resnet: update tinybox_red parameters to new best values (#4364) 1 year ago
- 27ee49b tensor variable (#4362) 1 year ago
- d2f8961 remove aql remnants in amd (#4346) 1 year ago
- 0d33c54 kernel: change PADTO check to allow up to 4x padding (#4354) 1 year ago
- babe87a BERT: Checkpoint loading tests (#4359) 1 year ago
- c12bcab search: fix actions space checks to ignore TC axis and amt (#4360) 1 year ago
- fdc8fab disable flaky mac gpt2 beam benchmark and add back cifar mac with JIT=2 (#4358) 1 year ago
- d325be2 update docs (#4356) 1 year ago
- a2d8151 just get dtype from kwargs (#4355) 1 year ago
- a9a1fa6 wmma: add reduce axis choice to TC action space (#4328) 1 year ago
- 93abcd3 fix function.py sum backward without downcast_half (#4353) 1 year ago
- 18c61ce test/fuzz_linearizer: add --atol/rtol and change half distribution (#4352) 1 year ago
- 71ff68b dropout after eval step (#4351) 1 year ago
- 27613dd MLPerf BERT: Main training loop (#4288) 1 year ago
- 61c97d5 refactor ops_gpu ctypes (#4331) 1 year ago
- cc17976 all fusion opportunities (#4348) 1 year ago
- f363f39 fix dtype of const folded sum (#4349) 1 year ago
- bf412ae use tolist instead of numpy for extracting parameters in onnx (#4333) 1 year ago
- 774a9b0 override assign_target in fuzz_schedule (#4342) 1 year ago
- bb849a5 [MLPerf] UNet3D dataloader (#4343) 1 year ago
- 82d0ed3 cap default dataset wikipedia max_workers to 32 (#4345) 1 year ago
- c1d8d42 fix mean of half tensor if sum is greater than hlaf.max (#4327) 1 year ago
- e027879 hotfix: remove double assignment (#4340) 1 year ago