chenyu ab7dfd637b use float for acc dtype for half tensor sum ...

we previously only upcast uint and int, and half was using half for acc.
change to acc in float for precision. but cast the result back to half to match torch/jax output dtype

2024-01-04 13:12:22 -05:00

..

codegen

remove VariableOrNum from Node.substitute arg (#2995)

2024-01-03 17:02:25 -05:00

features

hotfix: make multitensor shard contiguous

2024-01-03 08:48:30 -08:00

nn

replace d[a] if a in d else b with d.get(a, b) (#2997)

2024-01-03 18:10:25 -05:00

renderer

refactor workitems (#2973)

2024-01-02 09:16:52 -08:00

runtime

make disk simpler (#3002)

2024-01-03 17:46:21 -08:00

shape

bump shapetracker simplify message to DEBUG >= 5 (#2998)

2024-01-03 20:00:36 -05:00

__init__.py

move dtypes to dtype.py (#2964)

2024-01-01 14:58:48 -08:00

device.py

fix some long lines in tests (#3006)

2024-01-03 23:53:33 -05:00

dtype.py

pass tuple for strs to startswith (#2986)

2024-01-02 19:51:15 -05:00

graph.py

hotfix: save lines in graph

2024-01-03 12:03:42 -08:00

helpers.py

pass tuple for strs to startswith (#2986)

2024-01-02 19:51:15 -05:00

jit.py

hotfix: don't jitcache with 1 kernel. improvements to hip sniffer

2024-01-03 19:17:08 -08:00

lazy.py

hotfix: all device canonicalize should be done in Tensor

2024-01-03 10:48:04 -08:00

mlops.py

grad -> grad_output in mlops for consistency (#2982)

2024-01-02 18:03:55 -05:00

ops.py

vars_from_ast -> LazyOp.vars (#2965)

2024-01-01 18:12:38 -05:00

realize.py

don't alloc for InterpretedASTRunner (#2999)

2024-01-03 17:05:53 -08:00

tensor.py

use float for acc dtype for half tensor sum

2024-01-04 13:12:22 -05:00