vLLM v0.34.0 ships extensible KV cache by default, drops Model Runner V1
vLLM v0.34.0 is out, publishing CUDA 13.0, ROCm 10.0, CPU and XPU wheels plus matching Docker images.
AI and the frontier tech around it, explained every morning
Stories about performance · 1 stories
vLLM v0.34.0 is out, publishing CUDA 13.0, ROCm 10.0, CPU and XPU wheels plus matching Docker images.