Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Implementations for Q4_0_8_8 quantization based functions in AVX2 SIMD architecture #8713

Merged
merged 4 commits into from
Sep 4, 2024
Merged

Implementations for Q4_0_8_8 quantization based functions in AVX2 SIMD architecture #8713

merged 4 commits into from
Sep 4, 2024

Commits on Sep 4, 2024

  1. Add AVX2 based implementations for quantize_q8_0_4x8, ggml_gemv_q4_0_… 

    …8x8_q8_0 and ggml_gemm_q4_0_8x8_q8_0 functions
    @Srihari-mcw
    Srihari-mcw authored and Srihari-mcw committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    0c81b7b View commit details
    Browse the repository at this point in the history

  2. Update code to fix issues occuring due to non alignment of elements t… 

    …o be processed as multiple of 16 in MSVC
    @Srihari-mcw
    Srihari-mcw authored and Srihari-mcw committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    49af3f5 View commit details
    Browse the repository at this point in the history

  3. Update comments and indentation

    @Srihari-mcw
    Srihari-mcw authored and Srihari-mcw committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    364dc96 View commit details
    Browse the repository at this point in the history

  4. Make updates to reduce number of load instructions

    @Srihari-mcw
    Srihari-mcw authored and Srihari-mcw committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    c950fc3 View commit details
    Browse the repository at this point in the history