Upcoming llm-d Events
Stay connected with the llm-d community at meetups, conferences, and workshops. All meetings are open to the public unless noted otherwise.
March 2026
llm-d Distributed Inference Meetup NYC
๐ IBM Innovation Studio, 1 Madison Ave, NYC
March 11, 2026 ยท Free
Sessions
- Intro to llm-d for Open Source Distributed Inference & Project UpdateWed, Mar 11, 2026 ยท 5:15 PM ET ยท ๐ IBM Innovation Studio
- Distributed LLM Serving on AMD with llm-dWed, Mar 11, 2026 ยท 5:35 PM ET ยท ๐ IBM Innovation Studio
- The Path to Intelligent Routing: Lessons Learned Scaling Wide-EP and MoE ModelsWed, Mar 11, 2026 ยท 5:55 PM ET ยท ๐ IBM Innovation Studio
- KV-Cache Wins You Can See: Prefix-Cache Scheduling, Offloading, and ScalingWed, Mar 11, 2026 ยท 6:15 PM ET ยท ๐ IBM Innovation Studio
KubeCon + CloudNativeCon Europe 2026
๐ Amsterdam, The Netherlands
March 23โ26, 2026 ยท Paid
Sessions
- Panel: Routing Intelligence Vs Traffic Control: Architectural Tradeoffs for AI Inference in Gateway APIMon, Mar 23, 2026 ยท 12:45 โ 13:20 CET ยท ๐ Hall 7 | Room B
- Cloud Native Theater | Istio Day: Running State of the Art Inference with Istio and llm-dTue, Mar 24, 2026 ยท 16:00 โ 16:35 CET ยท ๐ Halls 1-5
- Route, Serve, Adapt, Repeat: Adaptive Routing for AI Inference Workloads in KubernetesWed, Mar 25, 2026 ยท 11:45 โ 12:15 CET ยท ๐ Auditorium
- Tutorial: KV-Cache Wins You Can Feel: Building AI-Aware LLM Routing on KubernetesThu, Mar 26, 2026 ยท 11:00 โ 12:15 CET ยท ๐ Elicium 1
- Evolving KServe: The Unified Model Inference Platform for Both Predictive and Generative AIThu, Mar 26, 2026 ยท 11:00 โ 11:30 CET ยท ๐ E103-105
April 2026
PyTorch Conference Europe 2026
๐ Paris, France
April 7โ8, 2026 ยท Paid
Sessions
- Why WideEP Inference Needs Data-Parallel-Aware SchedulingTue, Apr 7, 2026 ยท 13:35 โ 14:00 CEST ยท ๐ Central Room
- The Token Slice: Implementing Preemptive Scheduling Via Chunked DecodingTue, Apr 7, 2026 ยท 14:05 โ 14:30 CEST ยท ๐ Central Room
- Lightning Talk: Beyond Generic Spans: Distributed Tracing for Actionable LLM ObservabilityTue, Apr 7, 2026 ยท 15:45 โ 15:55 CEST ยท ๐ Master Stage
- Birds of A Feather: Disaggregated Tokenization: Building Toward Tokens-In-Tokens-Out LLM InferenceWed, Apr 8, 2026 ยท 10:10 โ 10:35 CEST ยท ๐ TBA
- Lightning Talk: KV-Cache Centric Inference: Building a State-Aware Serving Platform With llm-d and vLLMWed, Apr 8, 2026 ยท 11:10 โ 11:20 CEST ยท ๐ Founders Cafe
- Lightning Talk: Not All Tokens Are Equal: Semantic KV-Cache for Agentic LLM ServingWed, Apr 8, 2026 ยท 11:25 โ 11:35 CEST ยท ๐ Founders Cafe
- Lightning Talk: Inside vLLM's KV Offloading Connector: Async Memory Transfers for Higher Inference ThroughputWed, Apr 8, 2026 ยท 14:20 โ 14:30 CEST ยท ๐ Central Room