← Back to the list
P

pi-prefix-cache-compaction

Pi compaction that reuses the model server's prefix cache (vLLM, SGLang, llama.cpp, or hosted APIs with automatic caching such as DeepSeek; Anthropic Messages and OpenAI Chat Completions): no cold re-prefill of the history, a warm-up so the next turn star

Weekly downloads
564
Monthly downloads
1.5k
Stars
0
Users (7 days)
0
Likes
0

Install

Pi
pi install npm:pi-prefix-cache-compaction
Version
0.6.1
Publisher
jagdeeppb31
License
MIT