Fix docstring and default for MPS matmul

[christiangnrd]

Embarassing bugfix and make defaults match MPS defaults

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 80.96%. Comparing base (239fa4d) to head (21e27ee).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #723   +/-   ##
=======================================
  Coverage   80.96%   80.96%           
=======================================
  Files          62       62           
  Lines        2837     2837           
=======================================
  Hits         2297     2297           
  Misses        540      540           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[github-actions]

Metal Benchmarks

Details

Benchmark suite	Current: 21e27ee	Previous: 239fa4d	Ratio
latency/precompile	24155904250 ns	24383716541 ns	0.99
latency/ttfp	2292948125 ns	2324081375 ns	0.99
latency/import	1410318895.5 ns	1427504083 ns	0.99
integration/metaldevrt	839834 ns	837292 ns	1.00
integration/byval/slices=1	1552104 ns	1598354 ns	0.97
integration/byval/slices=3	8228979 ns	19021791.5 ns	0.43
integration/byval/reference	1548583.5 ns	1590708.5 ns	0.97
integration/byval/slices=2	2554041.5 ns	2727250 ns	0.94
kernel/indexing	583041.5 ns	459062.5 ns	1.27
kernel/indexing_checked	573459 ns	463104.5 ns	1.24
kernel/launch	11958 ns	11625 ns	1.03
kernel/rand	558750 ns	526667 ns	1.06
array/construct	6125 ns	5958 ns	1.03
array/broadcast	595083 ns	545375 ns	1.09
array/random/randn/Float32	767729.5 ns	886167 ns	0.87
array/random/randn!/Float32	616000 ns	578875 ns	1.06
array/random/rand!/Int64	544687.5 ns	539083 ns	1.01
array/random/rand!/Float32	574625 ns	533229.5 ns	1.08
array/random/rand/Int64	764083.5 ns	887000 ns	0.86
array/random/rand/Float32	637895.5 ns	840959 ns	0.76
array/accumulate/Int64/1d	1260270.5 ns	1292146 ns	0.98
array/accumulate/Int64/dims=1	1829375 ns	1865375 ns	0.98
array/accumulate/Int64/dims=2	2145438 ns	2215437 ns	0.97
array/accumulate/Int64/dims=1L	11668354 ns	12096125 ns	0.96
array/accumulate/Int64/dims=2L	9576750 ns	10003417 ns	0.96
array/accumulate/Float32/1d	1089270.5 ns	1086042 ns	1.00
array/accumulate/Float32/dims=1	1536417 ns	1581542 ns	0.97
array/accumulate/Float32/dims=2	1859229 ns	1998167 ns	0.93
array/accumulate/Float32/dims=1L	9821604 ns	10248396 ns	0.96
array/accumulate/Float32/dims=2L	7224291 ns	7422792 ns	0.97
array/reductions/reduce/Int64/1d	1520792 ns	1312917 ns	1.16
array/reductions/reduce/Int64/dims=1	1072667 ns	1120125 ns	0.96
array/reductions/reduce/Int64/dims=2	1128458.5 ns	1153917 ns	0.98
array/reductions/reduce/Int64/dims=1L	2007937.5 ns	2041417 ns	0.98
array/reductions/reduce/Int64/dims=2L	4477729.5 ns	3778125 ns	1.19
array/reductions/reduce/Float32/1d	1032958 ns	796167 ns	1.30
array/reductions/reduce/Float32/dims=1	817041 ns	794000 ns	1.03
array/reductions/reduce/Float32/dims=2	845708 ns	818562.5 ns	1.03
array/reductions/reduce/Float32/dims=1L	1313875 ns	1329000 ns	0.99
array/reductions/reduce/Float32/dims=2L	1786709 ns	1796708.5 ns	0.99
array/reductions/mapreduce/Int64/1d	1527041 ns	1298666 ns	1.18
array/reductions/mapreduce/Int64/dims=1	1080375 ns	1086313 ns	0.99
array/reductions/mapreduce/Int64/dims=2	1119417 ns	1122666 ns	1.00
array/reductions/mapreduce/Int64/dims=1L	2016959 ns	2025395.5 ns	1.00
array/reductions/mapreduce/Int64/dims=2L	3603875 ns	3647583 ns	0.99
array/reductions/mapreduce/Float32/1d	998834 ns	774083.5 ns	1.29
array/reductions/mapreduce/Float32/dims=1	823250 ns	791417 ns	1.04
array/reductions/mapreduce/Float32/dims=2	846083 ns	826542 ns	1.02
array/reductions/mapreduce/Float32/dims=1L	1312541 ns	1322667 ns	0.99
array/reductions/mapreduce/Float32/dims=2L	1801166.5 ns	1817916.5 ns	0.99
array/private/copyto!/gpu_to_gpu	637917 ns	533917 ns	1.19
array/private/copyto!/cpu_to_gpu	776875 ns	690271 ns	1.13
array/private/copyto!/gpu_to_cpu	793708 ns	668542 ns	1.19
array/private/iteration/findall/int	1577917 ns	1565687.5 ns	1.01
array/private/iteration/findall/bool	1408542 ns	1465333.5 ns	0.96
array/private/iteration/findfirst/int	2060542 ns	2079042 ns	0.99
array/private/iteration/findfirst/bool	2025000 ns	2020083 ns	1.00
array/private/iteration/scalar	3988458 ns	2787125 ns	1.43
array/private/iteration/logical	2614917 ns	2599208 ns	1.01
array/private/iteration/findmin/1d	2220125 ns	2265458 ns	0.98
array/private/iteration/findmin/2d	1503750 ns	1528791 ns	0.98
array/private/copy	569479 ns	847041.5 ns	0.67
array/shared/copyto!/gpu_to_gpu	83208 ns	84333 ns	0.99
array/shared/copyto!/cpu_to_gpu	81875 ns	83042 ns	0.99
array/shared/copyto!/gpu_to_cpu	81458 ns	83479.5 ns	0.98
array/shared/iteration/findall/int	1574562.5 ns	1558208 ns	1.01
array/shared/iteration/findall/bool	1434750 ns	1470708 ns	0.98
array/shared/iteration/findfirst/int	1632916 ns	1682792 ns	0.97
array/shared/iteration/findfirst/bool	1616458 ns	1644334 ns	0.98
array/shared/iteration/scalar	204958 ns	202000 ns	1.01
array/shared/iteration/logical	2242083 ns	2368458 ns	0.95
array/shared/iteration/findmin/1d	1811750 ns	1845542 ns	0.98
array/shared/iteration/findmin/2d	1513125 ns	1521583 ns	0.99
array/shared/copy	252000 ns	210959 ns	1.19
array/permutedims/4d	2359875 ns	2473375 ns	0.95
array/permutedims/2d	1138083 ns	1178666.5 ns	0.97
array/permutedims/3d	1667833 ns	1780750 ns	0.94
metal/synchronization/stream	18833 ns	19334 ns	0.97
metal/synchronization/context	20000 ns	20000 ns	1

This comment was automatically generated by workflow using github-action-benchmark.