sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) #1422
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.)
a8cee861
metal : allow env metal variable to override resource path (#1415)
592aed14
sync : restore common / main from `master`
68dd17b2
sync : restore whisper from `master`
e2c06e8f
talk-llama : update to latest llama.cpp
b3fc77c3
ruby : fix build
e39d42bf
ggml : fix 32-bit ARM build
002aeb72
ggml : fix MIN / MAX macro collisions + update ios bindings
d7735f84
ggml : fix ifdefs and MIN / MAX again
4bd643f0
ggerganov
force pushed
from
a237db63
to
4bd643f0
2 years ago
exampels : fix Obj-C and Swift examples
72c86970
ggml : fix 32-bit ARM compatibility
db1093e3
ggerganov
force pushed
from
2aac9af1
to
db1093e3
2 years ago
ggml : one more attempt to fix 32-bit ARM compat
36f375b2
whisper : fix support for larger graphs
0a7eba83
ggerganov
marked this pull request as ready for review 2 years ago
ggerganov
merged
f96e1c5b
into master 2 years ago
ggerganov
deleted the sync branch 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub