github-featured / ollama--ollama

发布

0 发布 616 Git 标签

RSS 订阅源
  • v0.15.0-rc5 912d984346
    比较

    llama: fix fattn-tile shared memory overflow on sm_50/52 (#13872)

    frostbyte_neo 发布于 2026-01-24 03:22:32 +00:00

    Use nthreads=128 for ncols=4 configurations in flash attention tile
    kernel to reduce shared memory usage below 48KB limit on Maxwell
    architectures (sm_50/52).

    With nthreads=256 and ncols=4, np=2 which caused shared memory to
    exceed 48KB. With nthreads=128 and ncols=4, np=1 keeps shared memory
    under the limit.

    下载附件