SGLang团队用Agent自动化优化推理管道，实测吞吐涨71%，TTFT砍半，还省了10GB显存，硬核经验值得看。
SGLang团队发布博客，介绍如何将基准测试、性能分析和内核优化知识转化为可执行的Agent技能。通过allreduce融合，Qwen3-Next吞吐量提升71.4%，TTFT从456ms降至168ms。路由token化去重使长上下文提示的TTFT降低29-49%。Spectral Progressive Diffusion实现2.32倍扩散去噪加速；KDA-Pilot在10个B200内核任务上获得1.13-2.75倍加速，3个PR已合并。LTX-2 VAE解码加速1.41倍，峰值内存节省9.7 GiB，所有改进均通过严格验证。
🚀 New blog: Agent-Assisted SGLang Development, the…
🚀 New blog: Agent-Assisted SGLang Development, the story of how we turn benchmarking, profiling, and kernel optimization know-how into executable agent skills.
Agent-assisted workflows are saving our team massive engineering hours while delivering major gains across the stack: ⚡️ +71.4% throughput & TTFT 456→168ms for Qwen3-Next via allreduce fusion ⚡️ 29–49% TTFT reduction on long-context prompts via router tokenization deduplication ⚡️ Up to 2.32x diffusion denoising speedup via Spectral Progressive Diffusion ⚡️ 10 B200 kernel tasks at 1.13x–2.75x speedups via KDA-Pilot; 3 PRs merged upstream ⚡️ 1.41x faster LTX-2 VAE decode, saving 9.7 GiB peak memory
And rigor is built into every step: benchmarks are fixed before any patching, baseline and candidate share the same ABI, and every change must be backed by profile evidence, eliminating benchmark reward hacking. Each iteration passes a Humanize/RLCR review loop before proceeding.
Read the full blog to see how we're rethinking development workflow 👇