SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nex

export SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1

python3 -m sglang.launch_server \
    --model Qwen/Qwen3-30B-A3B-Instruct-2507 \
    --speculative-algorithm EAGLE3 \
    --speculative-draft-model-path lmsys/SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nex \
    --speculative-num-steps 3 \
    --speculative-eagle-topk 1 \
    --speculative-num-draft-tokens 4 \
    --tp 4

# clone specforge
git clone https://github.com/sgl-project/SpecForge.git
cd SpecForge/benchmarks

# run benchmarks
python bench_eagle3.py \
        --model Qwen/Qwen3-30B-A3B-Instruct-2507 \
        --speculative-algorithm EAGLE3 \
        --speculative-draft-model-path lmsys/SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nex \
        --port 30002 \
        --config-list 8,0,0,0 8,3,1,4 8,5,1,6 8,5,3,6 8,7,1,8 8,7,4,8 \
        --benchmark-list gsm8k math500 mtbench humaneval livecodebench financeqa gpqa \
        --dtype bfloat16 \
        --tp 4 \
        --name qwen3-30b-a3b-spec-bundle