SGLang support?
Does this model can work with SGLang? when I try to use it i got an error for the quantized precision on startup
for rtx5090 i use docker image lmsysorg/sglang:dev-cu13-dev-qwen36-27b-nvfp4 with start command '/bin/sh
-c
ln -sf libnvidia-ml.so.580.105.08 /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1 && sglang serve --model-path /models/nvidia/Qwen3p6-27B-NVFP4
--served-model-name nvidia/Qwen3.6-27B-NVFP4
--tp-size 2 --attention-backend flashinfer
--reasoning-parser qwen3
--tool-call-parser qwen3_coder
--speculative-algorithm EAGLE --speculative-num-steps 3
--speculative-eagle-topk 1 --speculative-num-draft-tokens 4
--mamba-radix-cache-strategy extra_buffer
--host 0.0.0.0 --port 30000 --enable-metrics' it works