Scoutari

AI builder 的決策情報台。

瀏覽

  • 今日情報
  • Skill 榜單
  • AI 週報
  • 關於與編輯方針
  • RSS

主題

  • 模型發布
  • API 與價格
  • MCP 與 Skills
  • AI Coding
  • 中國模型
  • 開源模型
  • Agent
  • Infra / 成本
  • 值得試用
© 2026 Scoutari · scoutari.com摘要由 AI 輔助生成，並始終附上原文連結。
情報模型收藏週報設定
Thursday, July 9, 2026Scoutari
Log inSign up
Sign up
ModelsSkill RadarSavedPersonalizeSubmit sourceLog in
IntelModelsSkill RadarWeeklySavedPersonalizeSubmit source
Back to timeline

Thu, July 901:17Open SourceModel releasesOpen sourceAgents

Ollama v0.31.2 Release: Agent Core Integration, CUDA Fallback, and More

View originalGet it on GitHub

Decision Brief

What changedOllama v0.31.2 includes Agent core integration, CUDA fallback, Flash Attention enablement, MLX rewrite, and various fixes.
Why it mattersAgent core integration and CUDA fallback improve JetPack environment support and long-running automation for local Ollama developers.
Who should careOpen-source model users, Inference / infra teams
Affected stackOllamaLlamaNVIDIA
Builder actionUpgrade Ollama to v0.31.2
Source confidenceHigh · Official release / blog / repo

Key changes in v0.31.2: Agent core integration (#16963), fallback to standard CUDA when JetPack runner is missing (#16949), enable Flash Attention on CUDA CC 6.x GPUs (#16994), MLX rewrite (#16919) and update to de7b4ed9 (#17056), removal of OLLAMA_EXPERIMENT=client2 env var (#16962). Fixes include unbounded parallelism (#16966), CUDA toolkit lookup (#16613), UTF-8 safe file opening (#16999). Also cleaned up llama-server dead code (#17007) and unsupported ROCm devices (#17010). For developers deploying models locally with Ollama, the Agent core integration lays groundwork for advanced automation; CUDA fallback improves JetPack compatibility; Flash Attention enables better inference efficiency on older GPUs (CC 6.x). Overall, this is an important minor release toward greater stability and broader hardware support.

Summary basis: official / RSS sourceCompiled from the source scope noted above; the original remains authoritative.

Sources

  • Ollama（GitHub Releases）

    Local-model runtime releases: new supported models and serving features.

  • Ollama（GitHub Releases）

Related intel

  • Ollama v0.31.2: Agent Core Framework & GPU Flash Attention

    Ollama v0.31.2 introduces an Agent core framework and enables Flash Attention for CUDA CC 6.x GPUs, along with various fixes.

  • Ollama v0.31.2: GPU Compatibility Improvements and Core Agent Support

    Ollama v0.31.2 enhances CUDA and ROCm GPU support, enables Flash Attention for CUDA CC 6.x, and removes legacy code and experimental features.

  • Ollama v0.31.1 Boosts Gemma 4 Token Generation by Nearly 90% on Apple Silicon with Multi-Token Prediction

    Ollama v0.31.1 uses multi-token prediction to significantly accelerate Gemma 4 inference on Apple Silicon.

  • Porting Moebius 0.2B Image Restoration Model to Browser with Claude Code

    Author uses Claude Code to port the Moebius 0.2B image restoration model, originally dependent on PyTorch and CUDA, to run in browsers with WebGPU support.

留言

登入後即可留言，和其他 builder 交換實測心得。

還沒有留言，搶頭香。