huang3eng/SGLang-EAGLE3-Qwen3-Next-80B-A3B-Instruct-SpecForge

EAGLE3 For Qwen/Qwen3-Next-80B-A3B-Instruct

About

SpecBundle is an open-source initiative, jointly driven by the community and industry, to democratize speculative decoding by providing high-performance speculative decoding draft weights for mainstream open-source models.

Regenerated the responses in the mlabonne/open-perfectblend and trained the model on 1.4M data samples for 2 epochs. This checkpoint was trained using the SpecForge framework.

Usage

You can use this checkpoint with the command below.

python3 -m sglang.launch_server \
    --model Qwen/Qwen3-Next-80B-A3B-Instruct \
    --speculative-algorithm EAGLE3 \
    --speculative-draft-model-path huang3eng/SGLang-EAGLE3-Qwen3-Next-80B-A3B-Instruct-SpecForge \
    --speculative-num-steps 3 \
    --speculative-eagle-topk 1 \
    --speculative-num-draft-tokens 4 \
    --tp 8

Performance

This checkpoint exhibits superior performance on various benchmarks.