branch: master
Commits on master
- b46b8ee add a flag to log when beam surpassed max limit [pr] (#9533) 1 year ago
- eb95825 RetinaNet dataloader (#9442) 1 year ago
- 58206fa add amd llvm compiler (#9519) 1 year ago
- d8d65e2 update ruff to 0.11.2 (#9531) 1 year ago
- ee3ed73 add reorder_view matcher to scheduler [pr] (#9528) 1 year ago
- 8e555c5 switch quantization to unsigned/unsigned + add Ops.REDUCE (#9527) 1 year ago
- a35b0a8 am: just rename and reorder ip init funcs (#9504) 1 year ago
- 8a131ab am: allow allocations as small as a page (#9523) 1 year ago
- 3ad3ac4 Change dtypes.int to dtypes.ints (#9517) 1 year ago
- b9fab9b pin ruff to 0.11.0 in CI (#9520) 1 year ago
- 3c5161b add validation of the bounds of Ops.INDEX (#9503) 1 year ago
- 0b20f91 remove move_mask from the devectorizer (#9511) 1 year ago
- 9302738 hotfix: more consistent wgsl.py spacing + cleanups [pr] (#9515) 1 year ago
- 68053d0 dsp stuff / sniff ioctls from snpe (#9490) 1 year ago
- 2223b93 add UPat.or_casted [pr] (#9513) 1 year ago
- 1839e8c place masks in INDEX for TestGatedStoreRewrite [pr] (#9512) 1 year ago
- bd731a8 AMDCompiler refactor (no_comgr prereq) (#9497) 1 year ago
- 8c0d0a1 Add return_indices to max_pool (#9506) 1 year ago
- 189f62d add rounding to tqdm unit scale (#9507) 1 year ago
- a5c971f am: prereqs for rdna4 1/n (#9495) 1 year ago
- 1e5d9ad extra/gemm/max_matmul: start of custom kernels for GEMM (#6926) 1 year ago
- 865f23d olmoe memory usage cleanups 1 year ago
- 2c87a22 fix prg size calculation when there are adjacent mapped ranges (#9498) 1 year ago
- 1d71436 use libllvm19 in ci (#9494) 1 year ago
- a95b489 nanoGPT train works with tiny torch backend (#9283) 1 year ago
- f8976dd enable more webgpu tests (#9502) 1 year ago
- ae688e4 simple failing test for scheduling parallel reduce [pr] (#9501) 1 year ago
- e4dad99 nn.state docs cleanup (#8332) 1 year ago
- 1ea4876 olmoe touchups (#9499) 1 year ago
- f7506c6 JIT OLMoE (#9396) 1 year ago