Big news: XDP LightningAI was named “Data Center Innovation of the Year” in the 6th annual Data Breakthrough Awards! This marks the 3rd year one of our solutions has been honored by the premier program recognizing global data tech innovators. More here: bit.ly/4ln7on0

Next month is Dell Technologies World – where the top minds explore the tech simplifying AI adoption. We're excited to show how XDP LightningAI is redefining AI efficiency. Can’t wait? Learn more about XDP LightningAI here: bit.ly/3QIJYKM

Our CEO Ido Bukspan sat down w/ SemiWiki to talk XDP LightningAI – a game-changing memory tier w/ HBM-level performance for GPU workloads like LLM inferencing & RAG/VectorDB. Pushing the limits of AI & data-heavy apps? This is a must read! Check it out: bit.ly/42WjJaz

At #DellTechWorld, we’re showcasing how XDP LightningAI – running on NVIDIA Dynamo & vLLM Production Stack – delivers 2.5X+ performance improvements. Stop by our booth to see how we’re redefining efficiency & cutting TCO for enterprise AI. More: bit.ly/4kmfPO4

LightningAI FusIOnX: Pushing the Boundaries of AI Inference Optimization Our LightningAI FusIOnX engineers have successfully contributed to vLLM, enabling dynamic loading of external KV connector implementations! github.com/vllm-project/v…

Happy 4th of July from the Pliops team!

LLM applications are growing, which leads to deployments of expensive and power-hungry GPUs at an unprecedented rate. Pliops's Moshe Twitto will explain how to minimize redundant computation and power consumption at #P99CONF. Sign up today! ow.ly/NBmu50WzxBI #ScyllaDB

Live from FMS: the Future of Memory and Storage : Pliops is redefining GenAI infrastructure. Booth #840 | Aug 5–7 - See XDP LightningAI + FusIOnX in action - tinyurl.com/bddahjfk #GenAI #AIInfrastructure #LLM #InferenceAtScale #Pliops #TechLeadership

FMS 2025: Best of Show Award Winners 2025. Leaders of Memory and Storage Technology... StorageNewsletter bit.ly/3Uken3S #FMS DDN Graid Technology Infinidat Pliops Ultra Accelerator Link UnifabriX VΛST Data Western Digital #ITPT The IT Press Tour

🏆 Pliops won “Best of Show” at FMS: the Future of Memory and Storage for our XDP LightningAI + FusIOnX stack! - Up to 8x faster inference. Rack-level power savings. globenewswire.com/news-release/2… #AIAccelerator #GenAI #BestofShow #LightningAI #FMS2025

If prefixes repeat, stop recomputing them. We tested a network attached KV cache on 4090s and wrote up what helped and what did not. medium.com/data-science-c…

Big shoutout to the Cloud Rift team—brilliant work showing how KV-cache offload can unlock massive memory for LLMs on RTX GPUs. Love seeing LightningAI in action! cloudrift.ai/blog/how-to-gi… #GenAI #KVCache #Pliops #LightningAI #FusIOnX

GenAI is scaling fast. Memory is the bottleneck. ⚡ Meet LightningAI by Pliops—built for LLMs, RAG & GNNs. 📍 Booth 728 | AI Infra Summit 2025 We’re showcasing: 🔹 Long-term memory 🔹 Rack-level simplicity 🔹 Future-proof architecture #GenAI #AIInfra #LLM #RAG #LightningAI

Shanah Tovah! 🍎🍯 Wishing everyone a sweet, innovative, and successful New Year from all of us at Pliops. Here’s to new beginnings and breakthrough moments! #RoshHashanah #Innovation #Pliops

Scaling real-time AI is enticing, but which strategies should you use to increase your chances for success? Magdalen Manohar, Chip Huyen, and Pliops's Eshcar Hillel will share their lessons learned at our free & virtual P99CONF. ow.ly/CeWl50WQpNr #ScyllaDB #P99CONF

🔥 Catch Eshcar Hillel, Principal Research Scientist at Pliops , speaking at #P99CONF on LLM KV Cache Offloading — a breakthrough for low-latency AI workloads. 📅 Oct 22–23 | 💻 Free & Virtual 🔗 Register: lp.scylladb.com/p99-conf-2025-… #AI #LLM #TechPerformance #Pliops #P99Conf2025

Accelerate AI inference with Pliops LightningAI! Boost performance, cut latency, and optimize GenAI workloads. Learn more: pliops.com/deep-long-term… #GenAI #AIInference #LightningAI #DataAcceleration #Innovation

Big news! @PliopsTech is teaming up with Korea’s J&Tech to supercharge #GenAI & #LLM inference. With LightningAI, we’re delivering: ⚡️ 9x lower latency ⚡️ 3.3x higher throughput ⚡️ Lower TCO & carbon footprint lnkd.in/gx7PbfE9 #AI #Inference #Pliops #AIAcceleration #vLLM