tokenspeed-mooncake 0.3.12.post20260725
Source: Pypi.org· July 25, 2026
A KVCache-centric Disaggregated Architecture for large-scale LLM inference and training.
This story was reported by Pypi.org. Read the full original article:
Read on Pypi.org More in AI Research
View allopen-research-lite 0.1.1
Token-Efficient Ingestion Middleware & Concept-Diff Engine for Deep Research AI Agents.
Pypi.org · Jul 26, 2026
open-research-lite 0.1.0
Token-Efficient Ingestion Middleware & Concept-Diff Engine for Deep Research AI Agents.
Pypi.org · Jul 26, 2026
open-research-lite added to PyPI
Token-Efficient Ingestion Middleware & Concept-Diff Engine for Deep Research AI Agents.
Pypi.org · Jul 26, 2026
cogmemory added to PyPI
Cognitive memory architecture for LLM agents with principled forgetting
Pypi.org · Jul 26, 2026