vLLM
Printed in News · vllm.ai
Publishes about 4 a week · last piece Oct 16, 2026
How often
about 4 a week, by the archive: 16 pieces since Sep 18, 2026.
12 weeks agothis week
Latest pieces
- Hyper Optimizing Kimi K3 in vLLM: Moving Fast and Responsibly
- Serving Reflection Beam on vLLM from Day 0
- Scaling Kimi K3 on AMD Instinct MI355X: Matching NVIDIA HGX B300 Throughput per GPU on AgentX
- Announcing Day 0 Support for NVIDIA Nemotron 3.5 Super VL on vLLM
- Day 0 support for Muse Spark Open on vLLM
- Finish RL Training Faster: Bitwise-Consistent, High-Performance, Agent-Driven
- Adaptive Verification Without a Confidence Head
- Push-Based KV Transfer to Improve TTFT and TPOT for Disaggregated Inference in vLLM
- Improve TTFT for Multi-Turn Agentic Workloads with Bi-Directional KV Transfer in vLLM
- vLLM Support for NVIDIA Vera Rubin NVL72: 7.8x Throughput over GB200 NVL72
- DeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0
- Taking vLLM Apart: A Practical Guide to Disaggregated Serving
- Watermarking in vLLM
- Announcing vllm-metal: Concurrent Serving on Apple Silicon
- PD Serving of Qwen3.8-2.4T
In these stories
In these topics
Pick one in My Edition to read it with its neighbors.