vLLM ships Day-0 support for Reflection-Beam-1.0, a 501B-param MoE with 1M context
vllm_project · x · 2026-10-16
vLLM announces Day-0 support for Reflection's Beam-1.0, a sparse MoE model with 501B total parameters (23B active per token) and a 1M-token context window, combining hybrid attention with Harmony-format reasoning and tool use.
Beam also gets Day-0 RL support in SkyRL covering LoRA, BF16 full fine-tuning and MXFP8 RL with vLLM rollouts. The vLLM team worked with Reflection and Inferact on the serving path, from fused kernels to DFlash speculative decoding.
More from Infra
- Meta's open Muse Spark needs 493GB of memory — far beyond any consumer laptop — TejasKumar_ · 2026-10-16
- CoreWeave plunges 20% as credit markets price >60% default odds; is this dot-com all over again? — kimmonismus · 2026-10-16
- 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