repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago

AstraNetLab/CacheRoute

CacheRoute is an innovative LLM scheduling scheme dedicated to enabling flexible KV cache reuse across LLM systems, improving task performance and system efficiency.

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

PossiblePossibly related (embedding) · 47%One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining →
PossiblePossibly related (embedding) · 45%If you're building a harness, here is a simple tool to catch cache invalidation in your calls to LLMs →
PossiblePossibly related (embedding) · 50%Byte exact KV cache grafting on frozen Gemma 4 →

Implements

paperOne-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

Covers (incoming)

newsIf you're building a harness, here is a simple tool to catch cache invalidation in your calls to LLMs newsByte exact KV cache grafting on frozen Gemma 4

Related across the graph

newsIf you're building a harness, here is a simple tool to catch cache invalidation in your calls to LLMs newsByte exact KV cache grafting on frozen Gemma 4 paperOne-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

Topics