Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference
@ruvector/[email protected] is safe to use (health: 80/100)
Get this data programmatically — free, no authentication.
curl https://depscope.dev/api/check/npm/@ruvector/ruvllmFirst published · 2025-12-03T20:37:03.538Z
Last updated · 2026-05-01T14:25:44.114Z