DeepSeek V4 in vLLM: Efficient Long-Context Attentionvllm-website-pdzeaspbm-inferact-inc.vercel.app·3 pts·zagwdt·0
EinsteinArena: Harnessing the collective intelligence of agents in the wildeinsteinarena.com·5 pts·zagwdt·0
Consistency diffusion language models: Up to 14x faster, no quality losstogether.ai·219 pts·zagwdt·96