kimi k2.5 eagle3 EU AI Act Compliance Profile

Model Overview

kimi-k2.5-eagle3 is an Eagle3 MTP draft model for accelerating inference of Kimi-K2.5, trained with TorchSpec — an online speculative decoding training framework that runs FSDP training and inference concurrently. If you find this draft model useful, please give our project TorchSpec a 🌟 on GitHub.

Training data is available at lightseekorg/kimi-mtp-dataset.

Training Setup

• Cluster: 4 nodes × 8× H200 (32 GPUs total)
• Training: 2 nodes (16 GPUs), FSDP
• Inference: 2 nodes (16 GPUs), Engine (TP=8 per node)
• Duration: ~14 hours per phase

Training ran in two phases, each 20k steps (~300k samples):

• Phase 1: Regenerated open-perfectblend dataset
• Phase 2: Mixed dataset (English, VL, Chinese, function-call, agent, creative writing)

All training responses were regenerated by Kimi-K2.5 via Engine to match the base model's exact token distribution.

Training Curves

The plots show loss, token acceptance accuracy, and simulated accept_length during training. Both eval sets contain 256 samples drawn from each phase's own training corpus.

Phase 1 (steps 0 → 20k):

Phase 2 (steps 20k → 40k):

Performance

The primary metric is accept_length — the average number of tokens accepted per speculation step with topk=1, num_steps=3, num_draft_tokens=4. Higher is better.

Benchmarks were run using SpecForge's bench_eagle3.py. BFCL v3 benchmarks (†) use a custom extension to the original script.

![accept_length by dataset and method](i

Your obligations as a kimi k2.5 eagle3 deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Base Model