Repository Showcase
A curated collection of interesting GitHub repositories
LMCache/LMCache
speeds up LLMs with fast key-value caching
Related repos
- semantic cache for LLM queries, speeds up GPT apps, cuts API costs
- Benchmark for LLMs on software engineering tasks
- efficient attention for long-context LLMs
- alternative to RAG for LLMs, skips real-time retrieval by caching knowledge in context
- a fast, simple key-value cache
- serialize repo files fast for LLMs
- Compress prompts up to 20x while keeping LLM performance intact
- open-source memory engine for LLMs and AI agents
- framework for fast, resource-efficient LLM inference on local hardware
- cloud native LSM key-value store with searchable compression and distributed compaction
