OpenTransformer
/

llama.cpp-prismml

Model card Files Files and versions

llama.cpp-prismml / ggml

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

OpenTransformer's picture

OpenTransformer

perf: optimized AVX2 kernel + COM6-inspired matmul dispatch (0.2 -> 3.43 t/s)

8f4b822 verified 3 days ago

cmake
Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp) 3 days ago
include
Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp) 3 days ago
src
perf: optimized AVX2 kernel + COM6-inspired matmul dispatch (0.2 -> 3.43 t/s) 3 days ago
.gitignore

56 Bytes
Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp) 3 days ago
CMakeLists.txt

20.9 kB
Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp) 3 days ago