llama.cpp
hip: fix bf16 WMMA operand vector type for gfx11/gfx12
#30885
Merged

hip: fix bf16 WMMA operand vector type for gfx11/gfx12 #30885

JohannesGaessler merged 1 commit into ggml-org:master from master
waltercool
waltercool waltercool requested a review 30 days ago
waltercool hip: fix bf16 WMMA operand vector type for gfx11/gfx12
c05cabcb
waltercool waltercool force pushed to c05cabcb 30 days ago
IMbackK
IMbackK approved these changes on 2026-10-20
github-actions github-actions added ggml
github-actions github-actions added CUDA
JohannesGaessler
JohannesGaessler approved these changes on 2026-10-23
JohannesGaessler JohannesGaessler merged 9145ddb9 into master 27 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone