metal: per-op source split + parallel compile (replay) #26561
forforever73
force pushed
from
864c08ed
to
2934b5b3
7 days ago
metal : per-op source split + parallel compile (#24021)
ff8169ce
metal: add col2im_1d op (f32/f16/bf16) (#25176)
d2112aa3
metal : add set_rows with src0 f16 (#25434)
f348d513
metal : add CONV_2D_DW (depthwise convolution) support (#21565)
7649856e
metal : add Q2_0 support (#25419)
0b6cbb57
metal: fuse snake activation (mul, sin, sqr, mul, add) (#25459)
b2d79a7e
ggml-metal: FWHT kernel for metal backend (#25924)
db0a8ce8
metal : port new kernels into the split sources
55224983
forforever73
force pushed
from
2934b5b3
to
55224983
7 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub