NVIDIA open-sources srt-slurm: YAML orchestration for inference on Slurm clusters
AccBalanced · x · 2026-08-29
SemiAnalysis highlights NVIDIA's open-source srt-slurm, a declarative YAML-based orchestration layer for production-style inference topologies. Running one inference server in a Slurm job is easy; coordinating across multiple containers and nodes is not. srt-slurm coordinates sbatch/srun, GPU placement, networking, readiness checks and cleanup for prefill/decode disaggregation, multiple workers, Dynamo frontends, KV-cache-aware routers, and KV-cache offloading services — useful for quickly deploying representative inference systems for testing or benchmarking on Slurm-based GPU clusters.
More from Infra
- Scobleizer: Qwen Cloud is natively built around AI for better agent integration — Scobleizer · 2026-08-29
- NVL72 Achieves Up to 30x Better Throughput per MW than GB300 on AgentX Benchmark — nvidia · 2026-08-29
- a16z Partner: Only 2% of US Electricians Certified for DC Power — GregCook2011 · 2026-08-29
- The 'Boring' Network That Saves GPU Training Runs: OOB Management Explained — AccBalanced · 2026-08-29
- Running Generalist Robot Policies on STM32 and ESP32 Chips — yacineMTB · 2026-08-29
- Privacy architecture builds user trust to share sensitive health data with AI — bgmshana · 2026-08-29