geohot 224bac0318 speed up Kimi K3 decode projections on MI350X

2026-08-10 06:13:24 -07:00

..

codegen

hcq2: fix beam (#17467)

2026-08-09 16:53:47 +03:00

engine

hcq2: timings (#17464)

2026-08-08 22:00:32 +03:00

llm

speed up Kimi K3 decode projections on MI350X

2026-08-10 06:13:24 -07:00

mixin

support symbolic shapes in copy (#17461)

2026-08-08 09:16:59 -07:00

nn

const_like cleanups [PR] (#17386)

2026-08-03 23:57:20 -04:00

renderer

fix AMD WMMA emulation and test in CI (#17184)

2026-08-04 23:25:32 -07:00

runtime

hcq2: timings (#17464)

2026-08-08 22:00:32 +03:00

schedule

add SPEC checking for the kernel graph (#17432)

2026-08-08 10:00:06 -07:00

uop

add SPEC checking for the kernel graph (#17432)

2026-08-08 10:00:06 -07:00

viz

viz: collapse PROGRAM nodes like CALL (codex) (#17438)

2026-08-07 11:44:34 +09:00

__init__.py

start function and add walk rewrite (#14992)

2026-02-25 13:56:27 +08:00

device.py

64-bit UOp.variable support, try 2 (#17256)

2026-07-29 14:39:36 -04:00

dtype.py

truncate float in DType.const [pr] (#17439)

2026-08-06 20:19:08 -04:00

function.py

UOp.is_invalid [PR] (#17351)

2026-08-01 02:36:32 -04:00

helpers.py

fix AMD WMMA emulation and test in CI (#17184)

2026-08-04 23:25:32 -07:00

py.typed

add a single py.typed (#6083)

2024-08-14 17:31:46 -07:00

tensor.py

remove contiguous from custom_kernel (#17149)

2026-08-07 11:20:59 +09:00