branch: master
Commits on master
- d97d5a7 Optimize PTX gated loads index calculation (#4304) 1 year ago
- c67b70c small scheduler refactor (#4569) 1 year ago
- 77aa865 use assign_targets in LazyOp creation (#4568) 1 year ago
- b0fa97e assert error detail in test_assign (#4567) 1 year ago
- 25ec40c cleanup dtype of tensor creation from list (#4566) 1 year ago
- 4e1135a assign buffer read/write tests (#4565) 1 year ago
- b660f60 all uops are now cachable (#4564) 1 year ago
- 02327b8 simple stuff from new_uops branch (#4563) 1 year ago
- f53a23d Test for optim assertion (#4558) 1 year ago
- d7670f8 quantized llama multilazybuffer fix (#4557) 1 year ago
- bcee474 fix error message (#4556) 1 year ago
- 01a0c1a slightly faster nf4 llama (#4542) 1 year ago
- 4c232dc refactor LoadOps scheduling (#4553) 1 year ago
- 3da152f scheduler docs 2 (#4551) 1 year ago
- e07c766 nf4 llama (#4540) 1 year ago
- 7a26bda move scheduleitem to schedule.py (#4541) 1 year ago
- 508e8a6 add cpu objdump to LLVM/CLANG (#4537) 1 year ago
- bed70b1 mlperf bert getenv-able EVAL_STEP_FREQ (#4534) 1 year ago
- 328b083 lil profiling script 1 year ago
- da10cf0 extra/threefry.py for mem usage (#4533) 1 year ago
- 8a0fb3d delete old extra/autopad.py (#4532) 1 year ago
- 04a4980 touchup bert script (#4531) 1 year ago
- 4871476 move copy kernel to out of schedule ordering (#4530) 1 year ago
- 2fb564c multi reduce linearizer tests start (#4529) 1 year ago
- 3cba229 test_linearizer_correctness (#4458) 1 year ago
- b3d9fd4 infra for testing linearizer correctness (#4528) 1 year ago
- 2f970a4 all realize 2 (#4527) 1 year ago
- d2c347f faster gather for bert (#4526) 1 year ago
- 922e6e0 hotfix: fix docs 1 year ago
- 347a3ac add renderer class (#4524) 1 year ago