集中查看 DeepSeek、智谱 GLM、通义千问、OpenAI 和 Claude 等大模型 API 的接口变更、模型开放、调用价格与服务故障消息。具体价格和可用性以原始公告为准。
First v2 release candidate. Pre-releases are opt-in only; `pip install mcp` still resolves to the stable 1.x line. ```bash pip install mcp==2.0.0rc1 # or uv add "mcp==2.0.0rc1" ``` The [documentation](https://py.sdk.modelcontextprotocol.io/v2/) has the full tu
## Announcements & Breaking Changes - Upgraded to **ONNX 1.22.0** and protobuf 6.33.5 ([#28754](https://github.com/microsoft/onnxruntime/pull/28754), [#29606](https://github.com/microsoft/onnxruntime/pull/29606), [#28967](https://github.com/microsoft/onnxrunti
Status: Resolved All impacted services have now fully recovered. Affected components Codex in ChatGPT Desktop (Operational) Batch (Operational) Realtime (Operational) Moderations (Operational) GPTs (Operational) Connectors/Apps (Operational) Sora (Operational)
Status: Resolved All impacted services have now fully recovered. Affected components Search (Operational) Chat Completions (Operational) Audio (Operational) Files (Operational) Fine-tuning (Operational) Embeddings (Operational) Moderations (Operational) Compli
Status: Resolved All impacted services have now fully recovered. Affected components Conversations (Operational) Connectors/Apps (Operational) VS Code extension (Operational) Codex API (Operational) ChatGPT Work (Operational) Images (Operational) Audio (Operat
Status: Resolved All impacted services have now fully recovered. Affected components Codex Web (Operational) CLI (Operational) VS Code extension (Operational) Codex API (Operational)
Status: Resolved All impacted services have now fully recovered. Affected components Images (Operational)
Status: Resolved All impacted services have now fully recovered. Affected components Login (Operational) Search (Operational) GPTs (Operational) Codex in ChatGPT Desktop (Operational) ChatGPT Work (Operational) Sites (Operational) Voice mode (Operational) Conv
## Highlight **Agent** - Support structured output (#2150) - Support environment information injection (#2134) **Workspace** - Support OpenSandbox (#1953), Daytona (#1943), K8s (#1933), Bubblewrap (#2051) **Tool** - Support PowerShell for Windows (#2132) **RAG
Status: Resolved Image generation functionality has fully recovered, and error rates have returned to normal levels. Affected components Images (Operational) Image Generation (Operational)
Status: Resolved All affected API Platform functionality has now fully recovered. Affected components Login (Operational) Login (Operational)
A vulnerability in the LightGlue model loading path of huggingface/transformers version 5.2.0 allows an attacker-controlled model repository to execute arbitrary code during model initialization. The issue arises because the `trust_remote_code` parameter, inte
Status: Resolved All impacted services have now fully recovered. Affected components Codex in ChatGPT Desktop (Operational) Search (Operational) Conversations (Operational) GPTs (Operational) Connectors/Apps (Operational) ChatGPT Atlas (Operational) File uploa
Second v2 beta. Pre-releases are opt-in only; `pip install mcp` still resolves to the stable 1.x line. ```bash pip install mcp==2.0.0b2 # or uv add "mcp==2.0.0b2" ``` The [documentation](https://py.sdk.modelcontextprotocol.io/v2/) has the full tutorial and API
## Highlight **Agent** - Support agent interruption with context handling #1995 **Longterm Memory Integration** - Integrate ReMe based longterm memory #1972 - Integrate agentic longterm memory #1927 **TTS** - Support OpenAI TTS API #1878 - Support DashScope Co
A critical remote code execution vulnerability exists in all versions of the HuggingFace transformers library prior to version 5.3.0. The vulnerability allows an attacker to craft a malicious `config.json` file containing the `_attn_implementation_internal` fi
## Major New Features **RAG Module** - Introduced a native RAG (Retrieval-Augmented Generation) module with full support for distributed, multi-tenant, and multi-session RAG services, significantly enhancing knowledge retrieval capabilities. **Long-Term Memory
Triton 3.7.1 is a patch release on top of 3.7.0. It fixes the following 2 regressions and contains no new features or API changes. ## Regression fixes - Add async read dependencies to FenceAsync — a missing fence between a shared-memory store (st.shared) and a
## Highlights This release features 8 commits from 6 contributors (1 new)! v0.22.1 is a patch release on top of v0.22.0 with targeted bug fixes plus a couple of additions: new model support for JetBrains' Mellum v2, zentorch-accelerated quantized linear infere
## 🚀 What's New in v1.14.2? v1.14.2 is a patch release focused on security hardening, workflow and knowledge reliability, observability fixes, agent groundwork, and deployment/runtime tuning after v1.14.1. ### 🔐 Security and administration - **Tenant-scoped
# PyTorch 2.12.0 Release Notes - [Highlights](#highlights) - [Backwards Incompatible Changes](#backwards-incompatible-changes) - [Deprecations](#deprecations) - [New Features](#new-features) - [Improvements](#improvements) - [Bug fixes](#bug-fixes) - [Performa
## 🚀 What's New in v1.14.1? v1.14.1 is a patch release focused on security hardening, workflow and knowledge-base stability, deployment cleanup, and continued UI platform migration after v1.14.0. ### 🔐 Security - **Self-hosted `SECRET_KEY` hardening** — Dock
## 🚀 What's New in v1.14.0? ### Collaboration Collaboration allows workspace members to edit the same workflow together, with synced graph updates, online presence, and shared visibility into who is working where. On self-hosted deployments, collaboration is
来源标注日期：2026-04-24（未提供具体时刻）。 The DeepSeek API now supports V4-Pro and V4-Flash, available via both the OpenAI ChatCompletions interface and the Anthropic interface. To access the new models, the base_url remains unchanged, and the model parameter should be set
### Summary of major features and improvements * #### More GenAI coverage and framework integrations to minimize code changes * New models supported on CPUs & GPUs: Qwen3 VL * New models supported on CPUs: GPT-OSS 120B * Preview: Introducing the OpenVINO backe
* Preview: NPU compiler integration with the NPU plugin enables ahead-of-time and on-device compilation without relying on OEM driver updates. This feature is enabled by default in this release package. * Known Issues * Component: optimum; ID: 179936 Descripti
# PyTorch 2.10.0 Release Notes - [Highlights](#highlights) - [Backwards Incompatible Changes](#backwards-incompatible-changes) - [Deprecations](#deprecations) - [New Features](#new-features) - [Improvements](#improvements) - [Bug fixes](#bug-fixes) - [Performa
> **_NOTE:_** Please continue using OpenVINO 2025.4 release unless you require the specific bug fixes addressed in the 2025.4.1 version. # Summary of improvements * Preview: Mixture of Experts (MoE) models optimized for CPUs and GPUs, validated for GPT-OSS 20B
来源标注日期：2025-12-01（未提供具体时刻）。 Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.2. deepseek-chat corresponds to DeepSeek-V3.2's non-thinking mode deepseek-reasoner corresponds to DeepSeek-V3.2's thinking mode DeepSeek-V3.2-Speciale is se
# PyTorch 2.9.0 Release Notes - [Highlights](#highlights) - [Backwards Incompatible Changes](#backwards-incompatible-changes) - [Deprecations](#deprecations) - [New Features](#new-features) - [Improvements](#improvements) - [Bug fixes](#bug-fixes) - [Performan
