chenyuandGitHub 10d642e174 fuzz linearizer transformation (#2188) ...

* fuzz linearizer transformation

* no standard normal for fp16

* work

* Interpreted start

* CPU and TORCH work

* fix MemBuffer with same idx

* id for failed kernels

* no image and variable for Interpreted

* symbolic shape

* IMAGE only for GPU

* Interpreted almost all good

* cleanup

* fix bufs_from_lin

* zero size

* some failed examples

* just Exception

* just test not pass

2023-11-09 08:03:27 -08:00

..

codegen

Merge pull request #2242 from chenyuxyz/mypy-casts

2023-11-08 20:04:46 -05:00

features

remove real_offset (#2234)

2023-11-07 17:30:53 -08:00

nn

Stable diffusion WebGPU port (#1370)

2023-11-03 18:29:16 -07:00

renderer

less phi, proper phi (#2241)

2023-11-08 16:13:43 -08:00

runtime

feat: remove cache_id (#2236)

2023-11-08 08:09:21 -08:00

shape

fuzz linearizer transformation (#2188)

2023-11-09 08:03:27 -08:00

graph.py

remove real_offset (#2234)

2023-11-07 17:30:53 -08:00

helpers.py

diskcache touchups (#2235)

2023-11-07 18:00:04 -08:00

jit.py

no to_underlying (#2222)

2023-11-05 21:34:20 -08:00

lazy.py

mypy check warn_redundant_casts

2023-11-08 15:06:55 -08:00

mlops.py

add mops to graph, refactor IMAGE (#2100)

2023-10-17 21:27:51 -07:00

ops.py

update debug prints

2023-11-07 17:47:25 -08:00

realize.py

Disable logging in early compile2 and lower kernel counts (#2090)

2023-10-16 20:15:24 -07:00

tensor.py

extract const if it's const (#2193)

2023-10-31 18:52:35 -07:00