llama.cpp
CUDA/HIP: add Q2_0 (PrismML ternary 1.58-bit) support
#25188

Open

CUDA/HIP: add Q2_0 (PrismML ternary 1.58-bit) support #25188

The-Monk wants to merge 2 commits into ggml-org:master from The-Monk:cuda-q2_0-ternary

CUDA/HIP: add Q2_0 (PrismML ternary 1.58-bit, g128) support

0c667f9e

github-actions added ggml

github-actions added CUDA

CUDA: add Q1_0/Q2_0 to RDNA4 MMVQ nwarps=8 whitelist

7486adae

Reviewers

No reviews

Assignees

No one assigned

Labels

ggml CUDA

Milestone

No milestone