|
apps
|
LLM speedup with two jits, prefill/rollout (#15153)
|
2026-03-05 16:21:09 +08:00 |
|
codegen
|
rename CAT to VCAT (#15167)
|
2026-03-06 18:46:28 +08:00 |
|
engine
|
min
|
2026-03-07 10:00:29 +08:00 |
|
mixin
|
move more to mixins (#14780)
|
2026-02-16 11:35:00 +08:00 |
|
nn
|
q5k is like q4k (#15155)
|
2026-03-05 17:02:49 +08:00 |
|
runtime
|
metal uint32 icb offset overflow (#15156)
|
2026-03-06 00:54:39 +03:00 |
|
schedule
|
early lower cat
|
2026-03-07 11:39:20 +08:00 |
|
uop
|
simpler
|
2026-03-07 10:11:21 +08:00 |
|
viz
|
simpler
|
2026-03-07 10:11:21 +08:00 |
|
__init__.py
|
start function and add walk rewrite (#14992)
|
2026-02-25 13:56:27 +08:00 |
|
device.py
|
feat: per device mem_used (#15100)
|
2026-03-03 01:31:28 -08:00 |
|
gradient.py
|
simpler
|
2026-03-07 10:11:21 +08:00 |
|
py.typed
|
add a single py.typed (#6083)
|
2024-08-14 17:31:46 -07:00 |
|
tensor.py
|
min
|
2026-03-07 10:00:29 +08:00 |