vLLM repo

Every row links to its source: receipts, not summaries.

1. 2026-10-03 00:00 UTCIQuest-Q1: How to Self-Host the 320B Agentic Coding Modelmindstudio.ai
2. 2026-10-02 19:55 UTCBuilding a High-Performance and Portable vLLM Linear Backend with Helionpytorch.org
3. 2026-09-30 00:00 UTCHow to Deploy IQuest-Q1 with SGLang or vLLMmindstudio.ai
4. 2026-09-26 00:00 UTCHow to Run Audio8 ASR Infinite Locally with vLLM or Dockermindstudio.ai
5. 2026-09-25 00:00 UTCHow to Run OrcaSAQ2 27B on a 16GB GPUmindstudio.ai
6. 2026-09-24 00:00 UTCWatermarking in vLLMvllm.ai
7. 2026-09-23 23:07 UTCInferact's TPU megakernel hits 709 tokens per second on Kimi K3runtimewire.com
8. 2026-09-23 00:00 UTCHow to Run MiMo-V2.6-Flash-RL Locally with vLLM or SGLangmindstudio.ai
9. 2026-09-22 15:45 UTCHardware-Agnostic Models in vLLMpytorch.org
10. 2026-09-22 13:45 UTCHow Shopify built a continual learning loop with PyTorch and vLLMpytorch.org
11. 2026-09-21 20:01 UTCParadigma releases Limite, a 1B model for high-throughput math reasoningruntimewire.com
12. 2026-09-21 00:00 UTCPD Serving of Qwen3.8-2.4Tvllm.ai
13. 2026-09-19 00:00 UTCQwen-Image-2.1 on vLLM — Serve command for GB300 NVL4recipes.vllm.ai
14. 2026-09-18 00:00 UTCScaling Multi-GPU Video Captioning with PyNvVideoCodec and vLLMvllm.ai
15. 2026-09-15 00:00 UTCvLLM x Novita AI: Chord, Faster INT4 MoE for Kimi K2.x. Up to 1.3x on H200, 2.15x on Untuned B300vllm.ai
16. 2026-09-10 00:00 UTCTiered KV Cache Offloading in vLLMvllm.ai
17. 2026-09-08 00:00 UTCGLM 5.3 Optimizations, Part 1: Hybrid HiSparse Offloading in vLLMvllm.ai
18. 2026-09-08 00:00 UTCvLLM x AgentX: Optimizing for Real-World Agentic Servingvllm.ai
19. 2026-09-07 00:00 UTCServing LLMs on Tenstorrent Hardware: Inside the vLLM TT Pluginvllm.ai
20. 2026-09-07 00:00 UTCGLM 5.3 Optimizations, Part 1: Hybrid HiSparse Offloading in vLLMvllm.ai
21. 2026-09-04 23:50 UTCNVIDIA says new optimizations make local agents up to 1.9x fasterruntimewire.com
22. 2026-09-03 16:00 UTCNVIDIA Brings Simplified Local AI Support To NVIDIA GPUs Carrying 24+ GB VRAM While vLLM & & llama.cpp Optimizations Boost Compute By Up To 1.9xwccftech.com
23. 2026-09-01 23:31 UTCMiniMax H3 generates a 10.125-second audiovisual file in under nine secondsruntimewire.com
24. 2026-09-01 07:46 UTCHow to Run GLM-5.3 Locally: Hardware, VRAM & Setup (2026)buildfastwithai.com
25. 2026-09-01 00:00 UTCMiniMax H3 on vLLM-Omni: From System-Wide Optimization to Real-Time Serving with FastVideo’s FastH3vllm.ai
26. 2026-08-28 21:30 UTCvLLM Sessions at PyTorch Conference North America 2026pytorch.org
27. 2026-08-23 00:00 UTCExploring Speculative Decoding in vLLM on AMD GPUsvllm.ai
28. 2026-08-21 00:00 UTCIsoExec: Unified Execution to Eliminate Trainer-Inference Mismatch in SkyRLvllm.ai
29. 2026-08-17 00:00 UTCDistributed Layerwise Offload: Scaling Toward 200B+ DiT Models Efficiently in vLLM-Omnivllm.ai
30. 2026-08-14 00:00 UTCAdaptive Verification in vLLM: DSpark confidence-scheduled verificationvllm.ai