Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding

NVIDIA 开发者 · 来源更新 2026/09/17 05:46

今日摘要使用自己的 API，仅供个人查看

来源摘要

Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. It’s...

阅读原始来源

来源: NVIDIA 开发者 · 官方来源
来源发布: 2026/08/27 01:07
来源更新: 2026/09/17 05:46
首次采集: 2026/09/19 12:56

本文为公开信息索引与摘要，详情及后续变化请以原始来源为准。

NVIDIA · 英伟达动态

通义千问 Qwen Code 发布: SDK TypeScript Release v0.1.13

## Bundled CLI Version This SDK release bundles CLI version: 0.24.1 Source: CLI built from source (same branch/ref as SDK) --- ## Bundled CLI Version This SDK release bundles CLI version: 0.23.3 Source: CLI built from source (same branch/ref as SDK) --- ## Bun

来源更新 2026/09/19 17:05国内查看原文

Agent 与开发工具通义千问 Qwen Code 发布官方来源

通义千问 Qwen Code 发布: Qwen Code Desktop v0.24.1

## What's Changed * fix(cli): scope the ACP permission queue to the session by @chiga0 in https://github.com/QwenLM/qwen-code/pull/11802 * feat(channels): add shared output modes with DingTalk support by @qqqys in https://github.com/QwenLM/qwen-code/pull/11822

来源更新 2026/09/19 16:40国内查看原文

Agent 与开发工具通义千问 Qwen Code 发布官方来源

通义千问 Qwen Code 发布: Release v0.24.1

## Highlights _See the complete change list below._ ## Breaking Changes - refactor(goal)!: stop emitting the active_goal stream event ([#12181](https://github.com/QwenLM/qwen-code/pull/12181)) by @qqqys ## Complete Change List ### Features - feat(workflows): l

来源更新 2026/09/19 16:20国内查看原文

Agent 与开发工具Ollama 发布官方来源

Ollama 发布: v0.34.3

## What's Changed `GET /api/show` now advertises each model's thinking controls and default: ```sh curl http://localhost:11434/api/show -d '{"model": "glm-5.3-flash:cloud"}' ``` ```json { "thinking": { "values": ["low", "high", "max"], "default": "max" } } ```

来源更新 2026/09/19 16:10国际查看原文

Agent 与开发工具OpenAI Codex 发布官方来源

OpenAI Codex 发布: 0.156.0-alpha.7

Release 0.156.0-alpha.7

来源更新 2026/09/19 12:19国际查看原文