vLLM(@vllm_project):5x lower token costs on DeepSeek V4 in one month! Highlighting the vLLM community at work: day-zero recipes, then relentless optimization across kernels, scheduling, and serving. Every PR counts. 🚀

2026.07.02 16:41

5x lower token costs on DeepSeek V4 in one month! Highlighting the vLLM community at work: day-zero recipes, then relentless optimization across kernels, scheduling, and serving. Every PR counts. 🚀

NVIDIA AI Infrastructure@NVIDIAAIInfra

2026.07.02 16:04

💡 Continuous software innovation is the force multiplier behind AI infrastructure — compounding inference performance, lowering cost per token, and increasing long-term value with every optimization. Open source accelerates this advantage. Leading AI frameworks like @PyTorch and inference engines such as @sgl_project and @vllm_project are built natively on NVIDIA CUDA, enabling research breakthroughs and software optimizations to unlock great performance on NVIDIA GPUs from day zero.