Xing-Chen Liu

The DeepSeek-V4.1-Flash model, a multimodal Mixture-of-Experts model with 552B backbone parameters and support for contexts of up to one million tokens, is introduced, substantially improving cost efficiency for agentic workloads and pushing the limits of KV cache compression.

Communication compression can significantly enhance performance in HPC and LLM workloads, but existing benchmarks fail to capture its true potential—CC-Bench changes that narrative.

Bridging the Understanding-Action Gap leads to a 4.5% revenue increase by refining recommendation policies through direct user feedback rather than linguistic reasoning alone.

Forget static KV cache compression – KVServe dynamically adapts compression strategies to your service context, slashing latency by up to 32.8x in disaggregated LLM serving.

Cut your debugging time: CCL-D slashes the diagnosis time for slow/hang anomalies in large-scale distributed training from days to just 6 minutes.