v1.7.17
vllm-project/vllmv1.7.17Aug 24, 2026by Ed1s0nZ
Upgrading?
AI Summary
An update to Eino that disables automatic checkpoint recovery to prevent stale checkpoint takeover and adds detailed token usage tracking per conversation turn.
Key Highlights
- Disabled automatic Eino checkpoint resume to prevent repeated old responses
- Added per-turn token usage statistics (input, output, cached, reasoning tokens)
- Includes model call counts for each conversation turn
New Features
- Token usage tracking (input, output, cached, reasoning)
- Checkpoint disable feature
Full Release Notes
这次修复关闭了聊天链路中的 Eino checkpoint 自动恢复，避免旧断点抢先恢复导致模型反复回复历史对话。 This update disables automatic Eino checkpoint resume in chat flows, preventing stale checkpoints from taking over and causing repeated old responses. 同时新增/完善了按轮次展示 Token 用量的统计能力，可查看每次对话的输入、输出、缓存、推理和模型调用次数。 It also adds/improves per-turn token usage tracking, showing input, output, cached, reasoning tokens, and model call counts for each conversation turn.
Related Repositories
public-apis/public-apis★ 491,133
A collective list of free APIs
NousResearch/hermes-agent★ 255,957
The agent that grows with you
yt-dlp/yt-dlp★ 200,052
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,490
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,703
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.