AITOPAI热报
Products

SGLang 优化 DeepSeek 推理，发布生产级 serving 方案

官方账号LMSYS Org (SGLang)@lmsysorg
Post
View the post
Why we picked it

LMSYS 给 SGLang 针对性优化了 DeepSeek 的推理，博客里有性能数据和具体工程手段，自己部署 DeepSeek 的可以直接抄作业。

LMSYS 团队宣布 SGLang 针对 DeepSeek 模型完成一系列推理性能优化，并在博客中公开了具体的性能测试结果和工程实现细节。优化内容涵盖 SGLang serving 栈的底层改动，目标是达到生产环境可用的部署水准。DeepSeek 侧此前的性能基线被 SGLang 进一步抬高，文中给出了两者对比的数据。

Image · LMSYS Org (SGLang)
Original · LMSYS Org (SGLang)

DeepSeek raised the bar, and SGLang pushed it even further 🧡

https://t.co/fvbYzGEsFC

Read our blog to learn more about the performance results, engineering optimizations, and how SGLang brings it all together in a production-ready serving stack!

#DeepSeek#SGLang#LMSYS#推理优化#开源模型

Keep reading

Recent stories with the same tag or section
ModelsBuildersSelected02:02
vLLM Matches DeepInfer on DeepSeek-V4.1-Flash Decode

An open-source inference stack catching up with a frontier lab's in-house engine means teams can serve DeepSeek-V4.1-Flash without relying on the vendor's own tooling. Engineers running self-hosted deployments in Singapore or ASEAN data centres can benchmark vLLM at DEP32 as a direct alternative to DeepInfer's EP64DP64 setup, avoiding engine lock-in while keeping comparable throughput at large batch sizes.

#vLLM#DeepSeek#DeepInfer#inference
官方账号vLLM@vllm_projectSource
ModelsUS vs ChinaMulti-source71°06:56
Chinese contentKimi K3.1 Pro 登顶 Artificial Analysis 网络防御开源模型榜首

Moonshot 的 Kimi K3.1 Pro 在网络防御基准拿了开源模型第一，CyberGym-E2E-AA 得分 95% 连 GPT-6 Sol 都被超过，不过单任务成本反而变贵了，这篇把各家分数和价格都列得很清楚。

#Kimi#Moonshot#DeepSeek#推理模型
Event
官方账号Artificial Analysis@ArtificialAnlys11 sourcesSource