October 2026

800 posts from 132 blogs.

September 2026

11 of 800 posts

vLLM BlogOct 23 GLM-5.3 Optimizations, Part 2: PCP, DCP, and Hybrid HiSparse on 16 H200svLLM serves GLM-5.3 on 16 H200s with PCP and DCP prefill and Hybrid HiSparse decode, reaching 1M-token contexts and 1.7–3.2× the per-user speed of data-parallel P/D on the AgentX agentic benchmark.vLLMRead

Infrastructure

vLLM BlogOct 23 vLLM Delivers Day-0 Support for MiniMax-M3.1-FlashDay-0 vLLM support for MiniMax-M3.1-Flash on NVIDIA Blackwell, NVIDIA Rubin, and AMD MI350-series GPUs, with NVFP4 MSA kernels, NVFP4 MegaMoE, DSpark speculative decoding, AgentX results, and day-0 RL.vLLMRead

Reliability and performance

vLLM BlogOct 21 Day-0 Support for Flint on vLLMvLLM supports both Flint checkpoints (40B total, 2.5B active) from day 0, decoding a single request at about 500 tokens/s on one GPU.vLLMRead

AI and agents

vLLM BlogOct 21 Announcing Humming: Fast, Flexible Kernels for Quantized InferenceIntroducing Humming, a quantized inference kernel library from Ant Group and the vLLM community, with broad GPU and quantization support, dense and MoE performance results, and vLLM integration.vLLMRead

Infrastructure

vLLM BlogOct 20 Introducing vLLM TorchTPUvllm-torchtpu is a new vLLM backend for Google Cloud TPUs built on TorchTPU, with Pallas kernels, multi-host parallelism, KV cache offloading, and disaggregated serving.vLLMRead

Reliability and performance

vLLM BlogOct 19 Achieving near-zero-downtime scaling in Elastic Expert ParallelismHow asynchronous preparation and NIXL EP enabled near-zero-downtime Elastic EP scaling in vLLM.vLLMRead

Reliability and performance

vLLM BlogOct 16 Serving Reflection Beam on vLLM from Day 0vLLM supports Reflection's Beam-1.0 (501B total, 23B active) from day 0, with agent-driven optimization that cut decode latency 2.71× and DFlash2 speculative decoding with adaptive verification.vLLMRead

Reliability and performance

vLLM BlogOct 16 Hyper Optimizing Kimi K3 in vLLM: Moving Fast and ResponsiblyHow agent-assisted CuTe DSL optimizations accelerate Kimi K3 decode on NVIDIA GB300, and how scoped changes, correctness tests, and reproducible benchmarks help ship them responsibly.vLLMRead

Reliability and performance

vLLM BlogOct 16 Scaling Kimi K3 on AMD Instinct MI355X: Matching NVIDIA HGX B300 Throughput per GPU on AgentXInside the Kimi K3 optimization effort: understanding the bottlenecks and the decisions that made inference fastervLLMRead

Product and company

vLLM BlogOct 15 Announcing Day 0 Support for NVIDIA Nemotron 3.5 Super VL on vLLMRun NVIDIA Nemotron 3.5 Super VL on vLLM for multimodal agent workflows with image, document, and video understanding, OpenAI-compatible serving, and multi-token prediction.vLLMRead

Data engineering

vLLM BlogOct 15 Day 0 support for Muse Spark Open on vLLMDay-0 vLLM support for Muse Spark Open: 816B MoE, 1M context, multimodal inputs, DSpark speculative decoding, NVIDIA and AMD serving, initial TPU support, and LoRA RL.vLLMRead