Together Compute unveils multi-node inference engine with near-linear scaling, adopted by SkyRL and NVIDIA Dynamo
togethercompute · x · 2026-07-30
Together Compute announced its inference engine achieves near-linear multi-node scaling: from 671 to 2,248 steps/min when scaling from 16 to 64 GPUs, with lead widening from 1.79x at 2 nodes to 2.39x at 8. The engine is drop-in compatible via a single programid field, supports KV offloading and speculative decoding, is format-agnostic with OpenAI chat completions support, and is already adopted by SkyRL and NVIDIA Dynamo.
Related event: Together AI Unveils ThunderAgent, Doubling Agent Inference Throughput(7 posts)→
More from Infra
- NVIDIA launches RTX Spark for local AI on Windows PCs — ostrisai · 2026-10-16
- SkyRL ships Day-0 RL support for Beam with +62% LoRA decode throughput in vLLM — vllm_project · 2026-10-16
- DFlash2 delivers up to 3.03x decode-only speedup for Beam across five benchmarks — vllm_project · 2026-10-16
- vLLM's Beam serving kernels cut GB200 forward time from 8.15 to 6.47 ms at TP8 batch 128 — vllm_project · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16