A collection of production-grade draft models for speculative decoding
-
lmsys/SGLang-EAGLE3-Llama-3.3-70B-Instruct-SpecForge
1B ⢠Updated ⢠237 -
lmsys/SGLang-EAGLE3-Llama-3.1-8B-Instruct-SpecForge
0.4B ⢠Updated ⢠209 -
lmsys/SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nex
0.2B ⢠Updated ⢠209 -
lmsys/SGLang-EAGLE3-Llama-4-Scout-17B-16E-Instruct-SpecForge
0.8B ⢠Updated ⢠43