llama.cpp
ggml-webgpu: add Q1_0 support
#22374
Merged
Overview
Commits
2
Changes
View On GitHub
Commits
  • add fast matmul matvec q1_0 kernel
    SharmaRithik committed 97 days ago
  • ggml-webgpu: drop redundant zero-fills in Q1_0 shmem init
    SharmaRithik committed 96 days ago
FAQ Terms Privacy Refunds Impressum
Loading