feat: extend QK-Clip to support MLA (MuonClip Algorithm 1) [skip-build] (#28) e8e2c81 unverified dongseokmotif Claude Sonnet 4.6 wyldecat github-actions[bot] commited on about 9 hours ago
Replace cpu_offload constructor param with turn_on/turn_off API (#26) 05a75f1 unverified wyldecat Claude Opus 4.6 (1M context) github-actions[bot] commited on 5 days ago
draft commit for cpu_offload (#23) 10848ab unverified TaehyunKim github-actions[bot] wyldecat Claude Opus 4.6 (1M context) commited on 8 days ago