branch: master
Commits on master
- 23445db no skipped tests in RHIP (#4337) 1 year ago
- e4befa4 Fix in `_reshape_mask` (#4332) 1 year ago
- 664b563 Add `insert_before` to Linearizer Functions (#4320) 1 year ago
- 3372bea reduce children fusion tests (#4321) 1 year ago
- f3de179 added the download if not present missing function (#4318) 1 year ago
- bc36940 fix (#4319) 1 year ago
- 8d1649d raise error when too many resources requested in nv (#4324) 1 year ago
- c6c12ba save schedule graph pre validation (#4317) 1 year ago
- 40264c7 Update index.md (#4315) 1 year ago
- 24a6342 add mem/s to external_benchmark_resnet (#4309) 1 year ago
- 1f2642c kernel: fix calculation of smem size to ignore UNROLL (#4308) 1 year ago
- de832d2 disable bfloat16 from ptx tests (#4305) 1 year ago
- ec65aea resnet stop the script once hit target (#4303) 1 year ago
- 1891ebb make ring allreduce chunks a multiple of 2^n if possible (#4302) 1 year ago
- 1e37c4a minor llm.c improvements 1 year ago
- 3ec4b74 JIT=2 for mac cifar benchmark (#4300) 1 year ago
- c2dbe2a new split reduce heuristic try 2 (#4294) 1 year ago
- f1ebcff Ptx beam fix (#4296) 1 year ago
- f9a7bad use LR=7 for resnet with BS=1536 (#4299) 1 year ago
- 9a47ed0 test crossing diamond assigns (#4298) 1 year ago
- 5ae252a use at least float32 for optim.lr (#4297) 1 year ago
- 6f792b7 More improvements for resnet layer bench (#4272) 1 year ago
- ac9464f allow specify number of beam workers (#4292) 1 year ago
- 74a1be8 test reduce graph permutations (#4291) 1 year ago
- 0f0627b add mnist tutorial 1 year ago
- d31e220 add mlperf-logging to setup.py mlperf (#4289) 1 year ago
- 6b8a859 fix lds size for amd (#4287) 1 year ago
- c11bad7 prepare mlperf submission (#4270) 1 year ago
- c606a0b Docs link fix (#4286) 1 year ago
- c1fbacb resnet benchmarks use DEFAULT_FLOAT=HALF (#4285) 1 year ago