LMSYS Org

@lmsysorg

Large Model Systems Organization: We developed SGLang @sgl_project (sglang.io), Chatbot Arena (now @arena), and Vicuna!

lmsys.org

Joined August 2024

Replies Reposts Media

LMSYS Org
@lmsysorg
Sep 10
Thrilled to see day-0 SGLang support for DeepSeek V4.1 Flash! Technical blog: lmsys.org/blog/2026-09-1… This is another leap for the DeepSeek family, with several new upgrades to the V4 stack: shared compressed KV, a two-stage sparse indexer, mHC, and Engram. SGLang supports the
SGLang
@sgl_project
Sep 10
DeepSeek V4.1 Flash weights are out! We are shipping day-0 inference and RL support in SGLang and Miles. V4.1 extends the V4 stack with compressed KV shared across layers, a two-stage sparse indexer, and a 196B Engram lookup memory. It is natively multimodal with 552B backbone
00:00
7
LMSYS Org
@lmsysorg
Aug 28
SGLang has day-0 support for GLM-5.3! Same runtime, same flags, production-ready on NVIDIA Blackwell and Hopper, and AMD MI300X/325X/355X. SGLang is also the rollout engine inside Slime, the framework @Zai_org used to post-train GLM-5.3, so the same runtime that generated the RL
SGLang
@sgl_project
Aug 28
GLM-5.3 weights from @Zai_org are live, with SGLang powering day-0 serving support! GLM-5.3 inherits every optimization and feature we battle-tested for GLM-5.2 over the past months. On real-world multi-turn agentic workloads, we measured 537.6 tok/s/user on NVFP4 and 413
00:00
11
LMSYS Org
@lmsysorg
Aug 28
🚀 Infer-forge: Harness, Loop, and Graph Engineering Around SGLang @ant_oss built a three-layer system for running long inference optimization work through agents without losing provenance: Harness for execution, Task Loop for one Task's contract, Task Graph for verified
9
LMSYS Org
@lmsysorg
Aug 27
🚀 New blog: MiniMax-H3 on 8×H200: 1.95× Lossless, Up to 6.24× at 0.76–0.91 SSIM Same prompts, seeds, resolution, FPS, and 50 denoising steps held fixed across six workloads: - Dense lossless path: 1.85–1.95× over Diffusers, no approximation - Step reuse + sparse attention:
6
LMSYS Org
@lmsysorg
Aug 26
Very excited to see native vision come to the @Zai_org GLM family, and impressed by the architecture work behind it! With SGLang features like RadixAttention and HiCache, GLM-5.3-Flash is one of the most efficient and capable choices for agentic work across coding and
SGLang
@sgl_project
Aug 26
GLM-5.3-Flash (320B-A18B) from @Zai_org drops today with day-0 support in SGLang. You may know it as ox-alpha from the past few days! 👀 It's the first native multimodal model in the GLM-5 series, able to review its own output visually and fix what's wrong. 🚀 It outperforms
3