Skip to content

Feature Request: Update Upstream llama.cpp #82

Description

@Godl1nk

Prerequisites

  • I am running the latest code. Mention the version if possible as well.
  • I carefully followed the README.md.
  • I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
  • I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

The new llama.cpp has enhanced performance on MTP AGAIN, do merge as soon as possible. Thanks

Motivation

.

Possible Implementation

.

Activity

  1. laurentftech commented on Jun 27, 2026

    @laurentftech

    Additionnally some improvements have been made on the upstream regarding cache invalidation (which is currently degrading prefill performance):

    Merged:

    ggml-org#24411

    ggml-org#24176

  2. ethernidee commented on Jul 1, 2026

    @ethernidee

    What is expected increase in speed?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions