TogetherAI open-sources XoRL: 0 train-infer mismatch for large MoE RL training
PandaAshwinee · x · 2026-08-18
TogetherAI released XoRL, an open-source distributed RL training framework that achieves 0 train-infer mismatch by aligning computations between its training engine and a SGLang-based inference engine, ensuring bitwise-identical logprobs.
In Wordle tasks using Qwen3.6-35B-A3B, eliminating mismatch improved the solve rate from 63.9% to 77.4%. The post discusses strategies like replaying router weights versus indices, concluding that 0 mismatch outperforms mitigation objectives like CISPO, though it currently incurs a significant throughput cost.
More from Infra
- First AA-AgentPerf results: NVIDIA Vera Rubin NVL72 delivers up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- Vera Rubin NVL72 first benchmarks: up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- NVIDIA Vera Rubin NVL72 hits up to 5.7x GB300 throughput per MW on agent benchmark — ArtificialAnlys · 2026-10-16
- 14 open-source LLM observability tools to know in 2026, from Langfuse to Laminar — TheTuringPost · 2026-10-16
- Local AI is a routing problem, not a privacy feature: where each task should run — bigdata · 2026-10-16
- Moving agent work from GPUs to CPUs for durable, predictable actions — cramforce · 2026-10-16