OpenTransformer
/

llama.cpp-prismml

Model card Files Files and versions

llama.cpp-prismml / ggml /src /ggml-cpu /arch /x86

871 kB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

OpenTransformer's picture

OpenTransformer

perf: maddubs kernel + nrc=4 multi-row for Q1_0_g128 (3.5-3.75 t/s)

570ff77 verified 30 days ago

cpu-feats.cpp

10.7 kB
Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp) about 1 month ago
quants.c

196 kB
perf: maddubs kernel + nrc=4 multi-row for Q1_0_g128 (3.5-3.75 t/s) 30 days ago
repack.cpp

665 kB
Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp) about 1 month ago