github-actions[bot]
commented
2 months ago Test Results
5 923 tests ±0 5 890 :white_check_mark: - 1 9m 18s :stopwatch: -13s 1 suites ±0 33 :zzz: +1 1 files ±0 0 :x: ±0
Results for commit 4f4c80ed. ± Comparison against base commit c12b29eb.
This pull request skips 1 test.
``` sparse.numba_backend.tests.test_compressed ‑ test_reductions_float16[f8-1-sum-kwargs0] ```:recycle: This comment has been updated with latest results.
Hi @willow-ahrens @hameerabbasi,
This PR adds the second example: MTTKRP (I followed http://tensor-compiler.org/docs/data_analytics.html formula).
On my machine the current setup (tensors' dimensions and density) Finch shows x6 speedup compared to Numba.