SGLang says its production stack now serves Reflection's Beam, a model built for software engineering and long-horizon agents, with day-0 support. The post describes Beam as delivering frontier-level inference efficiency with more intelligence per token and links a serving cookbook and a blog post for details.
The post shows Beam's serving path through SGLang, which matters for teams weighing day-0 deployment of an open agentic coding model.
SGLang powers Beam’s production API, with day-0 support now available to everyone!
Built for software engineering and long-horizon agents, Beam delivers frontier-level inference efficiency with more intelligence per token. Serve it on the same production-proven stack: http://docs.sglang.io/cookbook/autoregressive/Reflection/Beam-1_0
Read more: https://www.lmsys.org/blog/2026-10-16-beam
Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners. We're releasing: - Weights, tokenizer, and reference implementation - BF16, FP8 and NVFP4 weights and a DFlash2 drafter - The open source harness we built and trained Beam on: Mirror CLI Weights and model card on Hugging Face: https://huggingface.co/reflection
Source: SGLang · x.comPublished
