- Add DeepseekV4ForCausalLM vision tower (supports DeepseekV4-Flash-Vision-Exp)
- Add Lfm2ForCausalLM (LFM2.5 dense variant)
- Add Spark2_5ForCausalLM (Spark-X2.5)
- Add Glm4MoeLiteForCausalLM (GLM4.7-Flash)
- More accurate autosplit accounting
- Faster CPU offloading, better Intel support (AVX512BW tier)
- Fix VRAM leak after vision tower offloading
- Fix potential worker timeout when offloading large models to CPU
- Greatly reduced import time, vendor in subset of flash-linear-attention to avoid initializing whole library plus Transformers
- Other optimizations, fixes and QoL improvements
- New logo
- Add Torch 2.12 and 2.13 wheels, 2.7 retired (from next release)
Full Changelog: v1.4.8...v1.4.9