nano-lmcache good first issues (Python)

V0: vLLM KV connector research notes about 2 hours ago

documentation good first issue task area: vllm difficulty: medium

10

📚 An educational, step-by-step implementation of LLM KV cache reuse — 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

Sync the Chinese docs with English changes since 2aa6d0a about 15 hours ago

documentation good first issue area: docs

Dami-wq-k03/nano-lmcache

10

📚 An educational, step-by-step implementation of LLM KV cache reuse — 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

M6: Skip rewriting chunks that are already cached about 19 hours ago

good first issue task area: cache difficulty: easy

Dami-wq-k03/nano-lmcache

10

📚 An educational, step-by-step implementation of LLM KV cache reuse — 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

G6: Model-aware cache namespaces about 20 hours ago

good first issue task area: gpu difficulty: easy

Dami-wq-k03/nano-lmcache

10

📚 An educational, step-by-step implementation of LLM KV cache reuse — 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

Dami-wq-k03/nano-lmcache

Open Issues Need Help