@magnitudedev/cli@0.2.1
Rouf0x/splatfpv@magnitudedev/cli@0.2.1Sep 30, 2026by github-actions[bot]
Upgrading?
AI Summary
This patch release fixes critical stability issues where local models would hang indefinitely when handling concurrent requests and addresses failures in speculative decoding models during long prompts.
Key Highlights
- Fixed local model hanging when multiple requests arrive simultaneously (e.g., Qwen3.6 35B-A3B).
- Fixed speculative-decoding models failing mid-request with 'only a blocked last page is relocated'.
- Admission logic no longer waits on the running generation, allowing the engine to release work.
Full Release Notes
## 0.2.1 ### Patch Changes - [`0476b71`](https://github.com/magnitudedev/magnitude/commit/0476b71a0fb772245328529312a3392d77b630aa) Thanks [@anerli](https://github.com/anerli)! - - Fix the local model hanging forever when a request arrived while another was generating, as with Qwen3.6 35B-A3B: every later request waited without a response while the model still reported Ready, and the engine held a CPU core at 100%. Admission no longer waits on the running generation, and the engine can no longer wait on work only it could release. - Fix speculative-decoding models failing mid-request with "only a blocked last page is relocated" during long prompts.
Related Repositories
affaan-m/ECC★ 285,919
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
react/react★ 251,629
The library for web and native user interfaces.
nodejs/node★ 122,528
Node.js JavaScript runtime ✨🐢🚀✨
Leonxlnx/taste-skill★ 100,731
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
louislam/uptime-kuma★ 92,732
A fancy self-hosted monitoring tool