Reflection AI open-sources Beam under Apache 2.0 with 40+ ecosystem partners
zhyncs42 · x · 2026-10-16
Reflection AI announced Beam is now available across platforms with open weights under the Apache 2.0 license, in collaboration with an ecosystem of 40+ partners including deployment solutions like SGLang, vLLM, and TokenSpeed (confirmed by LightSeek's official repost).
The release includes:
- Weights, tokenizer, and reference implementation on Hugging Face
- BF16, FP8, and NVFP4 weight variants plus a DFlash2 drafter
- Mirror CLI, the open-source harness they built and trained Beam on
More from Infra
- MiniCPM-V 4.7 35B-A3B hits 17+ tokens/s on iPad with ~3GB memory — techNmak · 2026-10-16
- China rolls out 'token factories' and a 2026-28 token economy action plan — nordicinst · 2026-10-16
- Vercel Sandbox Drives go GA: attach TBs of data in sub-second, fork instantly — cramforce · 2026-10-16
- 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