SGLang publishes one-GPU Qwen3.8-27B recipes, claims 206.1 tokens per second
Ying Sheng and Banghua Zhu's inference project added NVFP4 and DFlash2 recipes, with project-reported throughput of 206.1 tokens per second on one RTX 5090.
By RuntimeWire Staff · Published

Ying Sheng and Banghua Zhu's inference project added NVFP4 and DFlash2 recipes, with project-reported throughput of 206.1 tokens per second on one RTX 5090.