DC AI 热点

精选

全部智能体与应用工程前沿研究与模型架构其他动态安全治理与商业生态算力与数据中心具身智能与智能硬件

1Black Forest Labs 推出开源具身智能模型 FLUX 3 Action81 热度 ⌁2谷歌云 API Gateway 支持 MCP：将 REST API 原生转化为 AI Agent 工具80 热度 ⌁3Sakana AI聘请AI先驱Jürgen Schmidhuber担任首席科学顾问80 热度 ⌁4谷歌、OpenAI与Anthropic拟联合组建AI安全标准自律组织SAFA79 热度 ⌁5Agent Plugins 1.0.0 发布：科技巨头联手推跨平台 Agent 技能与 MCP 打包规范78 热度 ⌁

全部语言仅中文10 条动态

来源筛选

9月24日2026-09-24

Ollama 更新✦ 精选规则精选12:45

v0.34.4

What's Changed Structured outputs on thinking models now apply in a single pass, making them faster and more reliable. Fixed intermittent "model not found" errors with a large local library Fixed the macOS app becoming unresponsive when checking if ChatGPT or Codex is running. Qwen 3.8 prompt processing is faster on Apple Silicon. Gemma 4 on Apple Silicon now picks the best image resolution per image, keeping more detail in high-resolution images. Updated llama.cpp, MLX, and XGrammar. Full Changelog : v0.34.3...v0.34.4

阅读原文 ↗# OpenAI # 通义千问

Ollama 更新✦ 精选规则精选07:36

v0.34.4-rc1: mlxrunner: Update XGrammar to 0.2.7 for structured outputs

We pick up schema fixes for typed dictionary values and short arrays.

阅读原文 ↗

9月23日2026-09-23

Ollama 更新✦ 精选规则精选08:53

v0.34.4-rc0: mlx: speed up Qwen 3.8 prompt processing (#18550)

mlx: speed up Qwen 3.8 prompt processing Use MLX's gated-delta kernel for long scans and fold dense MLP global scales into SwiGLU. address comments

阅读原文 ↗# 通义千问

Ollama 更新✦ 精选规则精选04:42

v0.34.3

What's Changed GET /api/show now advertises each model's thinking controls and default: Available in the CLI with: ollama show gemma4 thinking levels false, true default true Available in the API with: curl http://localhost:11434/api/show -d ' {"model": "glm-5.3-flash:cloud"} ' { "thinking" : { "values" : [ " low " , " high " , " max " ], "default" : " max " } } Also available on ollama.com directly for cloud models. Nemotron H vision models are now supported on Apple Silicon with MLX Ollama's macOS app will now no longer reopen windows you've closed when activating it Fix for model pulls from HuggingFace Full Changelog : v0.34.2...v0.34.3

阅读原文 ↗# Hugging Face

9月19日2026-09-19

Ollama 更新✦ 精选规则精选08:15

v0.34.3-rc1

server: allow registry cross-host redirects among allowlisted hosts (…

阅读原文 ↗

Ollama 更新✦ 精选规则精选05:10

v0.34.3-rc0

api: expose model thinking levels and defaults ( #18473 )

阅读原文 ↗

9月18日2026-09-18

Ollama 更新✦ 精选规则精选07:04

v0.34.2

What's Changed Added first-run setup when running ollama , with options to sign in or continue locally. Setup completion is shared with the desktop app on macOS and Windows. Added ollama://apps to open the desktop app’s Apps page directly on macOS and Windows. Fixed excessive memory growth during long generations with MLX speculative decoding. Updated llama.cpp. Full Changelog : v0.34.1...v0.34.2

阅读原文 ↗# AI 编程

Ollama 更新✦ 精选规则精选02:49

v0.34.2-rc3

cli: add first-run onboarding shared with the desktop app ( #18495 )

阅读原文 ↗

Ollama 更新✦ 精选规则精选00:45

v0.34.2-rc2: mlxrunner: Release freed KV buffers during speculative decode

The decode loop releases MLX's pool of freed buffers every 256 generated tokens, which is also how often the KV cache grows and drops its previous, smaller buffers. The check fires only when the token count lands exactly on a multiple of 256. Speculative decoding emits several tokens per round, so most rounds step over the boundary and the pool is never released. Each growth at a long context leaves several GB of buffers that no later allocation can reuse, so the runner's footprint keeps climbing over a long generation until the system runs out of memory. We now release the pool whenever a round crosses a multiple of 256 tokens, which is what

阅读原文 ↗# AI 编程

9月17日2026-09-17

Ollama 更新✦ 精选规则精选05:06

v0.34.2-rc1: mlxrunner: lay out model by contract, checkpoint and construction

model is one package with three jobs: the contract between the runner and the architectures, the opened checkpoint, and building nn layers from checkpoint tensors. Its files did not say which was which. base.go carried the folded package's name over the interfaces and the registry, root.go held the safetensors header scan next to Root, and quant.go mixed the nvfp4 global-scale helpers with quant parameter resolution. base.go becomes model.go, named for what it holds. root.go keeps Root and Open; TensorQuantInfo and the header scan join quant.go, so everything the checkpoint says about quantization is read and resolved in one file. The global-

阅读原文 ↗