chenyuandGitHub fdb1c2b1d9 move reduce over 0 len axis logic to lazy.py (#3188) ...

* move reduce over 0 len axis logic to lazy.py

this fixed uneven shard reduce case if the uneven one has length 0

* fix interpreted backends

* fix backwards for 0 shape tensors too

2024-01-20 00:13:03 -05:00

..

codegen

fix padto when with late reduce (#3180)

2024-01-19 14:01:44 -05:00

features

reenable padto to search action (#3183)

2024-01-19 14:17:53 -05:00

nn

sharding for llama (#3151)

2024-01-16 19:28:00 -08:00

renderer

wmma: enable METAL half tensor cores and clean up cstyle (#3095)

2024-01-12 16:25:28 -05:00

runtime

event driven hip (#3160)

2024-01-18 14:35:18 -08:00

shape

remove unused expr node (#3170)

2024-01-18 14:18:43 -08:00

__init__.py

move dtypes to dtype.py (#2964)

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

device.py

buffer copy refactor (#3187)

2024-01-19 20:21:24 -08:00

dtype.py

simplify dtype (#3137)

2024-01-15 16:27:43 -08:00

graph.py

remove unused expr node (#3170)

2024-01-18 14:18:43 -08:00

helpers.py

JIT cleanups (#3164)

2024-01-17 23:39:57 -08:00

jit.py

buffer copy refactor (#3187)

2024-01-19 20:21:24 -08:00

lazy.py

move reduce over 0 len axis logic to lazy.py (#3188)

2024-01-20 00:13:03 -05:00

mlops.py

Fix backward fn for < and == (#3037)

2024-01-14 20:39:52 -08:00

ops.py

remove unused reciprocal (#3053)

2024-01-09 08:59:04 -08:00

realize.py

buffer copy refactor (#3187)

2024-01-19 20:21:24 -08:00

tensor.py

move reduce over 0 len axis logic to lazy.py (#3188)

2024-01-20 00:13:03 -05:00