github-featured / ollama--ollama

发布

0 发布 616 Git 标签

RSS 订阅源
  • v0.3.5 15c2d8fe14
    比较

    server: parallelize embeddings in API web handler instead of in subprocess runner (#6220)

    frostbyte_neo 发布于 2024-08-11 18:57:10 +00:00

    For simplicity, perform parallelization of embedding requests in the API handler instead of offloading this to the subprocess runner. This keeps the scheduling story simpler as it builds on existing parallel requests, similar to existing text completion functionality.

    下载附件