Evan Reichard ef7f4191a1 chore(llama-swap): increase context window and add CUDA device ...

- Increased context window from 80k to 202,752 tokens
- Added CUDA device specification for GPU acceleration
- Optimized for GLM 4.7 Flash (30B) model performance

2026-01-29 21:15:19 -05:00

14 KiB

Raw Blame History

View Raw