Welcome! Type "help" for available commands.
$
Summary
SGLang serves Qwen3.8-27B, a 27B hybrid Gated Delta Networks vision-language model, on a single H200, RTX PRO 6000, RTX 5090, or DGX Spark.
Checkpoints come in BF16, FP8, and NVFP4 W4A4 with an in-checkpoint MTP head and 262,144-token native context. Deployment supports EAGLE or DSPARK speculative decoding and includes a Mamba SSM memory ratio calculator for GDN state pool sizing.