Kangwenqiao

Kangwenqiao/nano-lmcache

๐Ÿ“š An educational, step-by-step implementation of LLM KV cache reuse โ€” learn prefix caching, chunk keys, storage & eviction, from pure Python to GPU tensors and vLLM integration. Inspired by LMCache.

5 good first / help-wanted issues ยท Python ยท last activity Oct 20, 2026

educational kv-cache llm llm-inference lmcache prefix-caching python vllm
5 Open Issues Need Help Last updated: Oct 20, 2026

Open Issues Need Help

View All on GitHub
good first issue task area: cache difficulty: easy
Kangwenqiao/nano-lmcache
7

๐Ÿ“š An educational, step-by-step implementation of LLM KV cache reuse โ€” learn prefix caching, chunk keys, storage & eviction, from pure Python to GPU tensors and vLLM integration. Inspired by LMCache.

Python
#educational#kv-cache#llm#llm-inference#lmcache#prefix-caching#python#vllm
good first issue task area: cache difficulty: medium
Kangwenqiao/nano-lmcache
7

๐Ÿ“š An educational, step-by-step implementation of LLM KV cache reuse โ€” learn prefix caching, chunk keys, storage & eviction, from pure Python to GPU tensors and vLLM integration. Inspired by LMCache.

Python
#educational#kv-cache#llm#llm-inference#lmcache#prefix-caching#python#vllm
documentation good first issue task area: docs difficulty: easy
Kangwenqiao/nano-lmcache
7

๐Ÿ“š An educational, step-by-step implementation of LLM KV cache reuse โ€” learn prefix caching, chunk keys, storage & eviction, from pure Python to GPU tensors and vLLM integration. Inspired by LMCache.

Python
#educational#kv-cache#llm#llm-inference#lmcache#prefix-caching#python#vllm
documentation good first issue task area: docs difficulty: easy
Kangwenqiao/nano-lmcache
7

๐Ÿ“š An educational, step-by-step implementation of LLM KV cache reuse โ€” learn prefix caching, chunk keys, storage & eviction, from pure Python to GPU tensors and vLLM integration. Inspired by LMCache.

Python
#educational#kv-cache#llm#llm-inference#lmcache#prefix-caching#python#vllm
documentation good first issue task area: docs difficulty: medium
Kangwenqiao/nano-lmcache
7

๐Ÿ“š An educational, step-by-step implementation of LLM KV cache reuse โ€” learn prefix caching, chunk keys, storage & eviction, from pure Python to GPU tensors and vLLM integration. Inspired by LMCache.

Python
#educational#kv-cache#llm#llm-inference#lmcache#prefix-caching#python#vllm