- Support DeepseekV41ForCausalLM
- Support Lfm3ForCausalLM and Lfm3VlForConditionalGeneration
- Improved loop detection
- Greatly reduced VRAM usage during quantization
- Faster quantization capture pass
- Fixed disk cache eviction policy (prevent possible churn when switching between many models)
- More optimizations, bugfixes and QoL improments
Full Changelog: v1.6.5...v1.6.6