Hugging Face's logo

OpenTransformer
/
llama.cpp-prismml

Model card Files
xet
 Community
llama.cpp-prismml

Commit History

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

    OpenTransformer
    Verified signature
    570ff77

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

    OpenTransformer
    Verified signature
    165bcc5

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

    OpenTransformer
    Verified signature
    8f4b822

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

    OpenTransformer
    Verified signature
    9d7f7ca

  4. Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp)

    OpenTransformer
    Verified signature
    79d8a89

  5. Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp)

    OpenTransformer
    Verified signature
    c7a53cd

  6. Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp)

    OpenTransformer
    Verified signature
    03ba2cd

  7. initial commit

    OpenTransformer
    Verified signature
    e232c73