ggml-cuda: Add generic NVFP4 MMQ kernel #21074
JohannesGaessler
merged
19 commits into
ggml-org:master
from
michaelw9999:nvfp4-mmq-mma
Introduced NVFP4 generic MMQ kernel
94e58bec
Added extra FP8 guard, hope to solve ci HIP failure
2761dcaf
am17an
commented
on 2026-03-28
Rename tiles and use HIP_FP8_AVAILABLE
cbd9fba6
am17an
commented
on 2026-03-28
am17an
commented
on 2026-03-28
Removed remaning FP8 straggler and added const int
0d9292cf
Const
0018ce86
am17an
commented
on 2026-03-28
Removed DECL_MMQ_CASE artifact
592e18cc
Removed newline
1489ea54
Removed space after else
3177030d
IMbackK
commented
on 2026-03-28
Changed HIP FP8 NVFP4 conversion gate
ebe28e97
Added new line to bottom of mmq.cu 270
aa55cb35
Removed extra spaces
8af43252
Removed single space in front of else on line 814
d8c5b7b6
Added NVFP4 to generate cu script so HIP can see it, further tightene…
cba8605e
Include generated mmq-instance-nvfp4.cu
a2f724da
am17an
approved these changes
on 2026-03-29
Added NVFP4 mmq to HIP Check ignore list
4be4b92b
Update ggml/src/ggml-cuda/mmq.cuh
30d7c8c1
Update ggml/src/ggml-cuda/mmq.cuh
145d8f18
Update ggml/src/ggml-cuda/mmq.cuh
bf496f6a
Added function names to closing endif
e2babc37
JohannesGaessler
approved these changes
on 2026-04-01
Reviewers
Assignees
No one assigned
Labels
script
Nvidia GPU
python
ggml
Milestone
No milestone
Login to write a write a comment.
Login via GitHub