RSS Anyway logo
HotLatestFollowingStatusAbout

vllm.ai

Sign in to follow
vllm.ai
RSSAtomJSON
  1. 01.
    A Preview of Production-Scale Kimi K3 Support on vLLM
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jul 22
  2. 02.
    Beyond a Single Model: Building Mixture-of-Models Systems with vLLM Semantic Router
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jul 21
  3. 03.
    Keeping vLLM Production Quality: A Look Inside CI, Benchmarking, and the Release Process
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jul 16
  4. 04.
    TML Inkling on vLLM: Day-0 Support with Optimized Performance
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jul 15
  5. 05.
    vLLM x TileRT: Specialized Decode for Latency-Critical Serving
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jul 14
  6. 06.
    EAGLE-3 Speculative Decoding on AMD Instinct GPUs: Training and Serving with vLLM and AMD Quark
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jul 13
  7. 07.
    vime + ROCm: End-to-End RL Post-Training on AMD Instinct™ GPUs
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jul 10
  8. 08.
    vLLM × HPC-Ops: High-Performance Attention and MoE Backends from Tencent Hunyuan
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jul 6
  9. 09.
    Experience and Lessons Learned from Serving Multi-Stage Qwen3-Omni in vLLM-Omni
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jul 1
  10. 10.
    Micro-Agent: Beat Frontier Models with Collaboration inside Model API
    vllm.ai · /blog/rss.xml
    ▲ 81 · Jun 29 · 22 comments on HN
  11. 11.
    Engineering TTS Inference in vLLM-Omni
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 23
  12. 12.
    Beyond One Model: Fusion in vLLM Semantic Router
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 16
  13. 13.
    MiniMax M3 in vLLM: Day-0 Serving for 1M-Token Multimodal Reasoning
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 12
  14. 14.
    DiffusionGemma: The First Diffusion LLM (dLLM) Natively Supported in vLLM
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 10
  15. 15.
    Announcing vime: A Simple, Stable, and Efficient RL Framework for LLMs
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 9
  16. 16.
    vLLM Semantic Router v0.3 Themis: From Signals to Stateful Production Routing
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 5
  17. 17.
    Announcing Day-0 Support for NVIDIA Nemotron 3 Ultra on vLLM
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 4
  18. 18.
    Fast & Efficient LLM Inference with vLLM: A New Course with DeepLearning.AI
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 3
  19. 19.
    Accelerating vLLM-Omni Inference with AutoRound Quantization
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 2
  20. 20.
    Session-Aware Agentic Routing: Continuity-Aware Model Selection for Long-Horizon LLM Agents
    vllm.ai · /blog/rss.xml
    ▲ 0 · Jun 2
  21. 21.
    vLLM on the DGX Spark: Architecture, Configuration, and Local Evaluation
    vllm.ai · /blog/rss.xml
    ▲ 0 · May 31
  22. 22.
    Speculators v0.5.0: DFlash Support and Online Training
    vllm.ai · /blog/rss.xml
    ▲ 0 · May 28
  23. 23.
    From Text to Multimodal Routing: Hardening Vision Signals in vLLM Semantic Router
    vllm.ai · /blog/rss.xml
    ▲ 0 · May 28
  24. 24.
    Native RL APIs in vLLM
    vllm.ai · /blog/rss.xml
    ▲ 0 · May 28
  25. 25.
    Accelerating Laguna XS.2 Inference with vLLM, Speculators, and LLM Compressor
    vllm.ai · /blog/rss.xml
    ▲ 0 · May 28
  26. 26.
    EAGLE 3.1: Advancing Speculative Decoding Through Collaboration Between the EAGLE Team, vLLM, and TorchSpec
    vllm.ai · /rss
    ▲ 69 · May 26 · 23 comments on HN
  27. 27.
    vLLM x Novita AI: PegaFlow for Production-Grade External KV Cache
    vllm.ai · /blog/rss.xml
    ▲ 0 · May 18
  28. 28.
    Announcing VeRL-Omni: Easy, Fast, and Stable RL Training for Diffusion and Omni-Modality Models
    vllm.ai · /blog/rss.xml
    ▲ 0 · May 14
  29. 29.
    Elastic Expert Parallelism in vLLM
    vllm.ai · /blog/rss.xml
    ▲ 0 · May 14
  30. 30.
    vLLM Tops the Artificial Analysis Leaderboard
    vllm.ai · /blog/rss.xml
    ▲ 0 · May 11