PulseAugur
EN
LIVE 04:12:57

Ollama v0.40.7-rc1 optimizes MLX backend with deduplicated CUDA payloads

By PulseAugur Editorial · [1 sources] ·

Ollama has released version v0.40.7-rc1, which includes optimizations for its MLX backend. This update focuses on deduplicating CUDA runtime payloads by moving shared CUDA libraries into a common payload. The changes also ensure that MLX loading can correctly resolve these packaged dependencies, while keeping MLX-private libraries and JIT headers within the MLX overlay. AI

IMPACT Minor infrastructure improvement for Ollama users, enhancing efficiency for MLX backend operations.

RANK_REASON This is a release of a software version with technical improvements, not a core AI model release or significant industry event.

Read on Ollama — Releases →

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

Ollama v0.40.7-rc1 optimizes MLX backend with deduplicated CUDA payloads

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 release of a software version with technical improvements, not a core AI model release or significant industry event.
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
21 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. Ollama — Releases TIER_1 Română(RO) · dhiltgen ·

    v0.40.7-rc1: mlx: deduplicate CUDA runtime payloads (#17956)

    <ul> <li>Deduplicate MLX CUDA runtime payloads</li> </ul> <p>Move CUDA libraries shared by the GGML and MLX backends into the sibling CUDA payload, and teach in-process and subprocess MLX loading to resolve that packaged dependency directory.</p> <p>Keep MLX-private libraries and…

RELATED ENTITIES

RELATED TOPICS