SGLang-native diffusion transformer overrides converted with NVIDIA ModelOpt.
AI & ML interests
LLM, distributed systems
Recent Activity
Organization Card
The large model systems organization (LMSYS) develops large models and systems that are open accessible and scalable.
Learn more about us at https://lmsys.org.
A collection of production-grade draft models for speculative decoding
-
lmsys/SGLang-EAGLE3-Llama-3.3-70B-Instruct-SpecForge
1B • Updated • 400 -
lmsys/SGLang-EAGLE3-Llama-3.1-8B-Instruct-SpecForge
0.4B • Updated • 739 -
lmsys/SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nex
0.2B • Updated • 1.41k • 4 -
lmsys/SGLang-EAGLE3-Llama-4-Scout-17B-16E-Instruct-SpecForge
0.8B • Updated • 19
SGLang-native diffusion transformer overrides converted with NVIDIA ModelOpt.
A collection of production-grade draft models for speculative decoding
-
lmsys/SGLang-EAGLE3-Llama-3.3-70B-Instruct-SpecForge
1B • Updated • 400 -
lmsys/SGLang-EAGLE3-Llama-3.1-8B-Instruct-SpecForge
0.4B • Updated • 739 -
lmsys/SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nex
0.2B • Updated • 1.41k • 4 -
lmsys/SGLang-EAGLE3-Llama-4-Scout-17B-16E-Instruct-SpecForge
0.8B • Updated • 19
models 49
lmsys/hunyuanvideo-modelopt-fp8-sglang-transformer
Updated
lmsys/qwen-image-edit-modelopt-fp8-sglang-transformer
Updated
lmsys/qwen-image-modelopt-fp8-sglang-transformer
Updated
lmsys/wan22-t2v-a14b-modelopt-nvfp4-sglang-transformer
Updated
lmsys/flux1-dev-modelopt-nvfp4-sglang-transformer
Updated
lmsys/wan22-t2v-a14b-modelopt-fp8-sglang-transformer
Updated
lmsys/flux2-dev-modelopt-fp8-sglang-transformer
Updated
lmsys/flux1-dev-modelopt-fp8-sglang-transformer
Updated
lmsys/SGLang-EAGLE3-Qwen3-235B-A22B-Instruct-2507-SpecForge-Meituan
0.6B • Updated • 774 • 1
lmsys/SGLang-EAGLE3-Qwen3-Coder-30B-A3B-Instruct-SpecForge
0.2B • Updated • 445 • 4