[BugFix] Fix het lazy stack ops

[vmoens]

Note: prints of nested lazy stacks is broken

[github-actions]

$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of CPU Benchmark Tests

Total Benchmarks: 47. Improved: $\large\color{#35bf28}1$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_common_ops	1.0499ms	1.0220ms	978.4535 Ops/s	999.1627 Ops/s	$\color{#d91a1a}-2.07\%$
test_creation	4.7999μs	4.3883μs	227.8811 KOps/s	232.6772 KOps/s	$\color{#d91a1a}-2.06\%$
test_creation_empty	11.7058μs	11.3125μs	88.3977 KOps/s	90.4767 KOps/s	$\color{#d91a1a}-2.30\%$
test_creation_nested_1	21.1327μs	20.5429μs	48.6787 KOps/s	49.3337 KOps/s	$\color{#d91a1a}-1.33\%$
test_creation_nested_2	22.0027μs	21.6266μs	46.2394 KOps/s	47.2263 KOps/s	$\color{#d91a1a}-2.09\%$
test_clone	28.4546μs	27.4990μs	36.3649 KOps/s	37.5471 KOps/s	$\color{#d91a1a}-3.15\%$
test_getitem[int]	33.0192μs	32.4615μs	30.8057 KOps/s	30.8907 KOps/s	$\color{#d91a1a}-0.28\%$
test_getitem[slice_int]	73.1895μs	68.3819μs	14.6238 KOps/s	14.5562 KOps/s	$\color{#35bf28}+0.46\%$
test_getitem[range]	66.4809μs	65.8291μs	15.1909 KOps/s	15.2812 KOps/s	$\color{#d91a1a}-0.59\%$
test_getitem[tuple]	64.0397μs	63.1665μs	15.8312 KOps/s	15.9300 KOps/s	$\color{#d91a1a}-0.62\%$
test_getitem[list]	72.5791μs	56.6256μs	17.6599 KOps/s	17.7459 KOps/s	$\color{#d91a1a}-0.48\%$
test_setitem_dim[int]	73.1990μs	47.1737μs	21.1983 KOps/s	21.8904 KOps/s	$\color{#d91a1a}-3.16\%$
test_setitem_dim[slice_int]	0.1142ms	85.6788μs	11.6715 KOps/s	11.7827 KOps/s	$\color{#d91a1a}-0.94\%$
test_setitem_dim[range]	0.1356ms	77.7719μs	12.8581 KOps/s	13.1120 KOps/s	$\color{#d91a1a}-1.94\%$
test_setitem_dim[tuple]	0.1192ms	79.5123μs	12.5767 KOps/s	12.8940 KOps/s	$\color{#d91a1a}-2.46\%$
test_setitem	33.5835μs	32.6713μs	30.6079 KOps/s	31.7410 KOps/s	$\color{#d91a1a}-3.57\%$
test_set	77.7109μs	38.2407μs	26.1502 KOps/s	32.4972 KOps/s	$\textbf{\color{#d91a1a}-19.53\%}$
test_set_shared	0.1424ms	0.1399ms	7.1475 KOps/s	7.0815 KOps/s	$\color{#35bf28}+0.93\%$
test_update	35.7365μs	34.1496μs	29.2829 KOps/s	29.7834 KOps/s	$\color{#d91a1a}-1.68\%$
test_update_nested	51.8783μs	50.5533μs	19.7811 KOps/s	19.5251 KOps/s	$\color{#35bf28}+1.31\%$
test_set_nested	42.5744μs	41.6940μs	23.9843 KOps/s	24.7513 KOps/s	$\color{#d91a1a}-3.10\%$
test_set_nested_new	65.5511μs	59.6680μs	16.7594 KOps/s	17.2075 KOps/s	$\color{#d91a1a}-2.60\%$
test_select	0.1008ms	0.1002ms	9.9768 KOps/s	10.2213 KOps/s	$\color{#d91a1a}-2.39\%$
test_creation[device0]	1.1224ms	0.4249ms	2.3533 KOps/s	2.3774 KOps/s	$\color{#d91a1a}-1.01\%$
test_creation_from_tensor	0.5498ms	0.4027ms	2.4830 KOps/s	2.1453 KOps/s	$\textbf{\color{#35bf28}+15.74\%}$
test_add_one[memmap_tensor0]	43.9334μs	30.4702μs	32.8190 KOps/s	34.0314 KOps/s	$\color{#d91a1a}-3.56\%$
test_contiguous[memmap_tensor0]	8.7689μs	8.1129μs	123.2610 KOps/s	127.5079 KOps/s	$\color{#d91a1a}-3.33\%$
test_stack[memmap_tensor0]	0.1544ms	39.4094μs	25.3747 KOps/s	25.4780 KOps/s	$\color{#d91a1a}-0.41\%$
test_reshape_pytree	38.0665μs	35.9130μs	27.8451 KOps/s	28.6798 KOps/s	$\color{#d91a1a}-2.91\%$
test_reshape_td	51.8483μs	49.5414μs	20.1851 KOps/s	20.4285 KOps/s	$\color{#d91a1a}-1.19\%$
test_view_pytree	34.0395μs	33.0535μs	30.2540 KOps/s	30.6666 KOps/s	$\color{#d91a1a}-1.35\%$
test_view_td	9.5569μs	8.8542μs	112.9404 KOps/s	113.2393 KOps/s	$\color{#d91a1a}-0.26\%$
test_unbind_pytree	38.4465μs	37.2545μs	26.8424 KOps/s	27.4741 KOps/s	$\color{#d91a1a}-2.30\%$
test_unbind_td	0.1540ms	0.1500ms	6.6673 KOps/s	6.8372 KOps/s	$\color{#d91a1a}-2.49\%$
test_split_pytree	43.7794μs	41.8514μs	23.8940 KOps/s	24.2901 KOps/s	$\color{#d91a1a}-1.63\%$
test_split_td	0.1196ms	0.1177ms	8.4942 KOps/s	8.5346 KOps/s	$\color{#d91a1a}-0.47\%$
test_add_pytree	47.0733μs	45.0446μs	22.2002 KOps/s	22.7341 KOps/s	$\color{#d91a1a}-2.35\%$
test_add_td	64.3831μs	62.4276μs	16.0186 KOps/s	16.4166 KOps/s	$\color{#d91a1a}-2.42\%$
test_distributed	69.7990μs	69.7990μs	14.3269 KOps/s	14.7931 KOps/s	$\color{#d91a1a}-3.15\%$
test_tdmodule	51.0990μs	24.6616μs	40.5488 KOps/s	40.9115 KOps/s	$\color{#d91a1a}-0.89\%$
test_tdmodule_dispatch	41.2505ms	55.7931μs	17.9234 KOps/s	19.4652 KOps/s	$\textbf{\color{#d91a1a}-7.92\%}$
test_tdseq	0.1786ms	30.6602μs	32.6155 KOps/s	32.1887 KOps/s	$\color{#35bf28}+1.33\%$
test_tdseq_dispatch	95.3990μs	54.0545μs	18.4999 KOps/s	18.6912 KOps/s	$\color{#d91a1a}-1.02\%$
test_instantiation_functorch	1.6036ms	1.5204ms	657.7083 Ops/s	662.6847 Ops/s	$\color{#d91a1a}-0.75\%$
test_instantiation_td	6.0842ms	1.1985ms	834.3755 Ops/s	880.0086 Ops/s	$\textbf{\color{#d91a1a}-5.19\%}$
test_exec_functorch	0.1803ms	0.1743ms	5.7360 KOps/s	5.8828 KOps/s	$\color{#d91a1a}-2.49\%$
test_exec_td	0.3038ms	0.3011ms	3.3215 KOps/s	3.3892 KOps/s	$\color{#d91a1a}-2.00\%$

[github-actions]

$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of GPU Benchmark Tests

Total Benchmarks: 47. Improved: $\large\color{#35bf28}10$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_common_ops	1.7412ms	1.4958ms	668.5264 Ops/s	646.9268 Ops/s	$\color{#35bf28}+3.34\%$
test_creation	6.1950μs	3.9354μs	254.1028 KOps/s	217.0127 KOps/s	$\textbf{\color{#35bf28}+17.09\%}$
test_creation_empty	20.5381μs	11.6174μs	86.0781 KOps/s	75.4562 KOps/s	$\textbf{\color{#35bf28}+14.08\%}$
test_creation_nested_1	36.6261μs	23.2324μs	43.0433 KOps/s	38.2269 KOps/s	$\textbf{\color{#35bf28}+12.60\%}$
test_creation_nested_2	41.4152μs	23.6129μs	42.3497 KOps/s	34.9997 KOps/s	$\textbf{\color{#35bf28}+21.00\%}$
test_clone	45.4242μs	33.0175μs	30.2870 KOps/s	27.9657 KOps/s	$\textbf{\color{#35bf28}+8.30\%}$
test_getitem[int]	61.4114μs	43.9763μs	22.7395 KOps/s	23.6805 KOps/s	$\color{#d91a1a}-3.97\%$
test_getitem[slice_int]	0.1119ms	90.5720μs	11.0409 KOps/s	11.3994 KOps/s	$\color{#d91a1a}-3.14\%$
test_getitem[range]	0.1438ms	0.1168ms	8.5624 KOps/s	8.6275 KOps/s	$\color{#d91a1a}-0.75\%$
test_getitem[tuple]	0.1011ms	82.2942μs	12.1515 KOps/s	13.1245 KOps/s	$\textbf{\color{#d91a1a}-7.41\%}$
test_getitem[list]	0.1299ms	0.1052ms	9.5014 KOps/s	9.5453 KOps/s	$\color{#d91a1a}-0.46\%$
test_setitem_dim[int]	2.1241ms	71.9805μs	13.8926 KOps/s	14.8040 KOps/s	$\textbf{\color{#d91a1a}-6.16\%}$
test_setitem_dim[slice_int]	2.8672ms	0.1285ms	7.7814 KOps/s	8.1470 KOps/s	$\color{#d91a1a}-4.49\%$
test_setitem_dim[range]	9.8842ms	0.1392ms	7.1861 KOps/s	7.4844 KOps/s	$\color{#d91a1a}-3.99\%$
test_setitem_dim[tuple]	5.0997ms	0.1100ms	9.0939 KOps/s	9.4267 KOps/s	$\color{#d91a1a}-3.53\%$
test_setitem	56.7643μs	45.8520μs	21.8093 KOps/s	21.5682 KOps/s	$\color{#35bf28}+1.12\%$
test_set	0.1151ms	45.7297μs	21.8676 KOps/s	22.8544 KOps/s	$\color{#d91a1a}-4.32\%$
test_set_shared	0.3891ms	0.2851ms	3.5079 KOps/s	3.1937 KOps/s	$\textbf{\color{#35bf28}+9.84\%}$
test_update	0.1242ms	46.7934μs	21.3705 KOps/s	20.8710 KOps/s	$\color{#35bf28}+2.39\%$
test_update_nested	0.1193ms	67.8972μs	14.7282 KOps/s	14.0989 KOps/s	$\color{#35bf28}+4.46\%$
test_set_nested	90.0645μs	58.7392μs	17.0244 KOps/s	17.2272 KOps/s	$\color{#d91a1a}-1.18\%$
test_set_nested_new	0.1089ms	78.8169μs	12.6876 KOps/s	12.6587 KOps/s	$\color{#35bf28}+0.23\%$
test_select	0.1709ms	0.1252ms	7.9867 KOps/s	8.1071 KOps/s	$\color{#d91a1a}-1.48\%$
test_creation[device0]	1.6380ms	0.6179ms	1.6185 KOps/s	1.6349 KOps/s	$\color{#d91a1a}-1.00\%$
test_creation_from_tensor	0.8791ms	0.5796ms	1.7253 KOps/s	1.5934 KOps/s	$\textbf{\color{#35bf28}+8.28\%}$
test_add_one[memmap_tensor0]	80.0394μs	64.4643μs	15.5125 KOps/s	15.3387 KOps/s	$\color{#35bf28}+1.13\%$
test_contiguous[memmap_tensor0]	16.1741μs	11.6590μs	85.7708 KOps/s	73.6024 KOps/s	$\textbf{\color{#35bf28}+16.53\%}$
test_stack[memmap_tensor0]	0.2761ms	74.9104μs	13.3493 KOps/s	16.0926 KOps/s	$\textbf{\color{#d91a1a}-17.05\%}$
test_reshape_pytree	49.6243μs	38.4782μs	25.9887 KOps/s	25.7622 KOps/s	$\color{#35bf28}+0.88\%$
test_reshape_td	92.5585μs	66.4194μs	15.0558 KOps/s	16.1451 KOps/s	$\textbf{\color{#d91a1a}-6.75\%}$
test_view_pytree	56.8453μs	35.3719μs	28.2710 KOps/s	28.1142 KOps/s	$\color{#35bf28}+0.56\%$
test_view_td	12.2931μs	8.9310μs	111.9692 KOps/s	101.9729 KOps/s	$\textbf{\color{#35bf28}+9.80\%}$
test_unbind_pytree	66.5284μs	43.9337μs	22.7616 KOps/s	23.7802 KOps/s	$\color{#d91a1a}-4.28\%$
test_unbind_td	0.3461ms	0.2153ms	4.6439 KOps/s	4.9311 KOps/s	$\textbf{\color{#d91a1a}-5.82\%}$
test_split_pytree	98.4437μs	56.2513μs	17.7774 KOps/s	20.7696 KOps/s	$\textbf{\color{#d91a1a}-14.41\%}$
test_split_td	0.2361ms	0.1648ms	6.0661 KOps/s	6.2999 KOps/s	$\color{#d91a1a}-3.71\%$
test_add_pytree	70.4255μs	63.2403μs	15.8127 KOps/s	15.7246 KOps/s	$\color{#35bf28}+0.56\%$
test_add_td	0.1833ms	0.1113ms	8.9843 KOps/s	9.5092 KOps/s	$\textbf{\color{#d91a1a}-5.52\%}$
test_distributed	0.1625ms	0.1625ms	6.1538 KOps/s	5.6721 KOps/s	$\textbf{\color{#35bf28}+8.49\%}$
test_tdmodule	2.1849ms	39.0934μs	25.5798 KOps/s	27.3572 KOps/s	$\textbf{\color{#d91a1a}-6.50\%}$
test_tdmodule_dispatch	4.5261ms	82.1722μs	12.1696 KOps/s	12.4297 KOps/s	$\color{#d91a1a}-2.09\%$
test_tdseq	2.3490ms	49.0917μs	20.3700 KOps/s	20.7986 KOps/s	$\color{#d91a1a}-2.06\%$
test_tdseq_dispatch	6.1115ms	93.5635μs	10.6879 KOps/s	10.4861 KOps/s	$\color{#35bf28}+1.92\%$
test_instantiation_functorch	2.2201ms	1.8937ms	528.0589 Ops/s	551.3513 Ops/s	$\color{#d91a1a}-4.22\%$
test_instantiation_td	2.0751ms	1.4785ms	676.3503 Ops/s	695.7380 Ops/s	$\color{#d91a1a}-2.79\%$
test_exec_functorch	0.3449ms	0.2834ms	3.5292 KOps/s	3.7548 KOps/s	$\textbf{\color{#d91a1a}-6.01\%}$
test_exec_td	0.5581ms	0.4600ms	2.1740 KOps/s	2.2161 KOps/s	$\color{#d91a1a}-1.90\%$