llama.cpp
CUDA/HIP: fix ssm_scan on devices where warp size is not 32
#14196
Merged
Merged
CUDA/HIP: fix ssm_scan on devices where warp size is not 32 #14196
IMbackK
merged
1 commit into
ggml-org:master
from
IMbackK:ssm_scan
CUDA/HIP: fix ssm_scan on devices where warp size is not 32
036f66ea
JohannesGaessler
approved these changes
on 2025-06-15
Login to write a write a comment.
Login via GitHub