Sglang

The uncensored build of DeepSeek’s Vision-Exp is a byte-for-byte drop-in — which meant every failure afterwards was mine to fix. A sparse-MLA kernel that rejects vision prefill on SM120, a streaming tool-call parser that corrupted exactly the arguments coding agents live on, and a health check that proved the port but not the model. 142 tok/s single-stream, native vision, zero refusals, one new router feature.

Flash-Next is Qwen’s sparse-attention flagship and its official FP8 recipe assumes datacenter GB300. Adapting it to 2x96 GB workstation Blackwell took one legit trick (offloading the 51B-entry PLE n-gram table to pinned host RAM, freeing ~25 GiB per GPU for KV), one config archaeology exercise (YaRN via –hf-overrides because the build has no –rope-scaling flag), and discipline about what not to retry: fp8 KV hard-requires BF16 on QSA and fails differently on vLLM and SGLang, and 786K+ contexts OOM during compile no matter the KV math. Final stack: 512K context, 1.42M-token pool, 146.5 tok/s decode with MTP ns=3, 9-11.2K tok/s prefill, vision and tools validated. The SGLang NVFP4 day-0 lane runs too (after three SM120 gates), but serves one request at 262K slower than the vLLM lane serves two at 512K, so vLLM keeps the port.

Instead of picking one model per task, I made three machines cooperate: a big thinking model for primary reasoning, a fast local 27B for subagent loops and images, a router with automatic failover in front of everything, and shared agent memory. Total cost: electricity. Here is the full architecture, the benchmarks, and the lessons learned the hard way.