a1-agents-eagle3-speculator

EAGLE3 Speculator for Qwen3.5 MoE (a1-agents)

Trained using speculators library for speculative decoding with vLLM.

Model Details

• Verifier: Qwen3.5 MoE (Qwen3_5MoeForConditionalGeneration), 40 layers, 65.5 GB
• Draft type: EAGLE-3, 1 layer, draft vocab size 8192
• Target layers: [3, 19, 39]
• TTT steps: 3 (predicts 3 speculative tokens)
• Training data: 5000 ShareGPT samples
• Optimizer: Muon (muon_lr=1e-3, momentum=0.95)
• Attention: SDPA (required for GB10/Sm121)

Validation Metrics

• Mean acceptance length: 2.02
• Throughput speedup: 1.34x (on GB10, CUDAgraph enabled)

Usage with vLLM

from vllm import LLM, SamplingParams

llm = LLM(
    model="/path/to/verifier-model",
    speculative_config={
        "method": "eagle3",
        "model": "Ichigec/a1-agents-eagle3-speculator",
        "num_speculative_tokens": 3,
    },
    dtype="bfloat16",
    gpu_memory_utilization=0.65,
    max_model_len=8192,
    enforce_eager=False,  # CUDAgraph works for serving
)

Or with vLLM CLI:

vllm serve /path/to/verifier-model \
  --speculative_config '{"method": "eagle3", "model": "Ichigec/a1-agents-eagle3-speculator", "num_speculative_tokens": 3}' \
  --dtype bfloat16 \
  --gpu-memory-utilization 0.65 \
  --max-model-len 8192

Training Details

Trained on NVIDIA DGX Spark (GB10, 128GB unified memory) using the speculators offline pipeline.