The Large Model Systems Organization develops large models and systems that are open, accessible, and scalable.
Latest Blog
See all posts
XM-Sparse: Pushing the Throughput Frontier of Sparse Attention with Netpreme X-Mem™
XM-Sparse integrates Netpreme X-Mem™ with SGLang HiSparse. High-bandwidth access to offloaded KV caches reduces decode latency, while the added capacity supports larger batches and higher concurrency.
HiCache Across Multi-Parallelism and Distributed Serving
Agentic workloads repeatedly send long, mostly unchanged histories to the model. Radix cache reuses prefix KV in GPU memory, and HiCache extends that reuse to host memory and external storage.
Accelerating GLM-5.3-Flash on H200: High-Throughput Disaggregated Serving
GLM-5.3-Flash combines sparse attention, recurrent linear attention, and MoE. Serving it efficiently at long context lengths requires sufficient memory to sustain high concurrency, low execution cost per output token, and sufficient prefill throughput to keep decode busy.
Projects
View all projects
Our Sponsors & Partners
Backed by leading companies and institutions advancing AI research.
Voltage Park, NVIDIA, Nebius, Google Cloud, AtlasCloud, a16z, AMD, InnoMatrix, Laude Institute, Hyperbolic, NovitaAI, Verda Cloud, Sky9, Kaggle, MBZUAI, Together, RunPod, Anyscale, HuggingFace