SGLang-native diffusion transformer overrides converted with NVIDIA ModelOpt.
AI & ML interests
LLM, distributed systems
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 • 213 -
lmsys/SGLang-EAGLE3-Llama-3.1-8B-Instruct-SpecForge
0.4B • Updated • 467 -
lmsys/SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nex
0.2B • Updated • 8.2k • 3 -
lmsys/SGLang-EAGLE3-Llama-4-Scout-17B-16E-Instruct-SpecForge
0.8B • Updated • 91
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 • 213 -
lmsys/SGLang-EAGLE3-Llama-3.1-8B-Instruct-SpecForge
0.4B • Updated • 467 -
lmsys/SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nex
0.2B • Updated • 8.2k • 3 -
lmsys/SGLang-EAGLE3-Llama-4-Scout-17B-16E-Instruct-SpecForge
0.8B • Updated • 91
models 55
lmsys/SGLang-EAGLE3-Step-3.5-Flash-SpecForge-RadixArk
0.4B • Updated • 8
lmsys/qwen-image-edit-2511-modelopt-nvfp4-sglang
Image-to-Image • Updated • 1
lmsys/qwen-image-edit-modelopt-nvfp4-sglang
Image-to-Image • Updated
lmsys/qwen-image-2512-modelopt-nvfp4-sglang
Text-to-Image • Updated • 1
lmsys/qwen-image-modelopt-nvfp4-sglang
Text-to-Image • Updated
lmsys/Qwen3.5-397B-A17B-DFlash
Text Generation • 1B • Updated • 111 • 1
lmsys/hunyuanvideo-modelopt-fp8-sglang-transformer
Updated • 19 • 1
lmsys/qwen-image-edit-modelopt-fp8-sglang-transformer
Updated • 22 • 1
lmsys/qwen-image-modelopt-fp8-sglang-transformer
Updated • 20
lmsys/wan22-t2v-a14b-modelopt-nvfp4-sglang-transformer
Updated • 22 • 1