v0.4.1
SesameAILabs/csmv0.4.1Nov 10, 2025by github-actions[bot]
AI Summary
Fixes a critical memory issue on Blackwell GPUs where the RoPE (Rotary Positional Embedding) cache was incorrectly expanding to an excessively large size.
Key Highlights
- Resolves memory blow-up on Blackwell GPU builds.
- Prevents RoPE cache from growing to ~4e18 positions.
Full Release Notes
## Bug Fixes - avoid bogus RoPE expansions on Blackwell GPUs https://github.com/TimmyOVO/deepseek-ocr.rs/issues/24 Blackwell builds were blowing up memory because the RoPE cache tried to grow to ~4e18 positions.