Adrian KretzandGitHub 043d5f2cb5 Fix NOUNROLL (#1439)

2023-08-04 16:50:19 -07:00

..

codegen

Fix NOUNROLL (#1439)

2023-08-04 16:50:19 -07:00

nn

Add assert for wrong matmul/dot shapes (#1438)

2023-08-04 18:16:56 -04:00

runtime

Add ops_shm (#1413)

2023-08-03 17:40:52 -07:00

shape

Support constant expand to symbolic shape (#1411)

2023-08-02 21:21:22 -07:00

graph.py

Add WHERE ternary (or trinary?) op (#1196)

2023-07-16 00:31:55 -07:00

helpers.py

fix: Context (#1430)

2023-08-04 10:53:48 -04:00

jit.py

Enable JIT tests for supported devices, skip METAL and WEBGPU (#1265)

2023-07-18 11:40:37 -07:00

lazy.py

LazyBuffer.get_variable_buffers() (#1391)

2023-08-02 09:01:35 -07:00

mlops.py

Add WHERE ternary (or trinary?) op (#1196)

2023-07-16 00:31:55 -07:00

ops.py

fix: don't put kernels into cache when optimizing (#1409)

2023-08-02 18:17:16 -04:00

state.py

Add option in llama.py to quantize weights to int8 at runtime (#1289)

2023-07-24 17:22:38 -07:00

tensor.py

Add assert for wrong matmul/dot shapes (#1438)

2023-08-04 18:16:56 -04:00