repoGitHubTrust 82 · PrimaryPublished yesterdayLive · yesterday
Zefan-Cai/R-KV
[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Covers
Related to
Implements
Implements (incoming)
Related across the graph
paperCheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented ReasoningnewsDeepSeek-V4-Flash (MXFP4): compute buffer scales ~3x just from KV cache quant type (f16 vs q8_0) — anyone else seeing this? Llama.cpppaperMessage Passing Enables Efficient ReasoningpaperCARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear AttentionmodelRetrace-1.5BnewsNew benchmark exposes reasoning gaps in top models
