PulseAugur
EN
LIVE 18:33:34

llama.cpp b11985 optimizes Metal performance on Apple devices

By PulseAugur Editorial · [1 sources] ·

The llama.cpp project has released version b11985, introducing performance enhancements for Metal on macOS and iOS. This update includes faster MXFP4 matrix-vector multiplication by optimizing fp4 value decoding and removing threadgroup memory usage. Additionally, contiguous unary and binary operations now utilize full threadgroups, and GLU rows are split across threadgroups for improved efficiency. AI

IMPACT Optimizes LLM inference performance on Apple hardware, potentially enabling faster local model execution.

RANK_REASON This is a software release for an open-source project focused on optimizing inference for large language models on consumer hardware.

Read on llama.cpp — Releases →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

llama.cpp b11985 optimizes Metal performance on Apple devices

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This is a software release for an open-source project focused on optimizing inference for large language models on consumer hardware.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
12 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. llama.cpp — Releases TIER_1 (SO) · github-actions[bot] ·

    b11985

    <details open=""> <p>metal : faster MXFP4 mat-vec, full threadgroups for unary/binary/GLU (<a class="issue-link js-issue-link" href="https://github.com/ggml-org/llama.cpp/pull/31075">#31075</a>)</p> <ul> <li>metal : faster MXFP4 mat-vec kernel</li> </ul> <p>Decode the fp4 values …

RELATED ENTITIES

RELATED TOPICS