Tensormesh

LMCache is an open source Knowledge Delivery Network (KDN) designed as a caching layer for large language model serving that accelerates inference by reusing KV (key-value) caches across repeated or overlapping computations. It enables fast prompt caching, allowing LLMs to “prefill” recurring text only once and then reuse those stored KV caches, even in non-prefix positions, across multiple serving instances. This approach reduces time to first token, saves GPU cycles, and increases throughput in scenarios such as multi-round question answering or retrieval augmented generation. LMCache supports KV cache offloading (moving cache from GPU to CPU or disk), cache sharing across instances, and disaggregated prefill, which separates the prefill and decoding phases for resource efficiency. It is compatible with inference engines like vLLM and TGI and supports compressed storage, blending techniques to merge caches, and multiple backend storage options.

Telnyx is a global communications infrastructure platform that provides voice, messaging, networking, and AI-powered real-time communication capabilities through a fully owned telecom stack. The platform combines carrier-grade networking, programmable identity systems, AI inference, and low-latency communication infrastructure to support real-time conversational AI agents and enterprise communication workflows. Telnyx owns and operates its entire network stack, including physical infrastructure, mobile core systems, edge processing, and AI compute layers, enabling faster performance and lower latency without relying on third-party telecom providers. The platform offers tools such as voice agent builders, speech-to-text, text-to-speech, global phone numbers, AI orchestration, and programmable compliance controls for building intelligent voice and messaging systems.