#2727th of 31 in Training and fine-tuning
deepspec
Training and evaluation code for speculative-decoding draft models
- Stars
- 7.2k
- License
- MIT
- Last commit
- Jul 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
DeepSpec is a Python codebase for training and evaluating draft models used in speculative decoding. It covers data preparation (prompt download, answer regeneration with the target model, target cache), a training script that spawns one worker per GPU, and an eval script measuring acceptance on benchmarks such as gsm8k, math500 and humaneval. It implements DSpark, DFlash and Eagle3 and links released checkpoints on Hugging Face for Qwen3 and Gemma 4 targets.
Who it is for: Researchers and engineers training speculative-decoding draft models
Strengths
- Implements three draft algorithms (DSpark, DFlash, Eagle3) in one pipeline with per-model configs
- Released checkpoints on Hugging Face for Qwen3 4B/8B/14B and Gemma 4 12B
- Eval covers nine benchmarks, including gsm8k, humaneval, mt-bench and arena-hard-v2
- MIT license
Weaknesses
- Target cache for the default Qwen3-4B setup needs roughly 38 TB of storage
- Default configs assume a single node with 8 GPUs
- Data preparation needs a separately served inference engine for the target model
- No release tags; only four target models are covered by released checkpoints
What it needs
- GPU required
- Needs Inference engine to serve the target model (data prep), Hugging Face models and datasets
- Models: Qwen/Qwen3-4B, Qwen/Qwen3-8B, Qwen/Qwen3-14B, google/gemma-4-12B-it
Also in Training and fine-tuning
See all 31| Rank | Project | Score |
|---|---|---|
| 1 | unslothDesktop and web app to run, fine-tune and export open models | 88 out of 100 |
| 2 | deepspeedPyTorch library for distributed training of large models with ZeRO | 84 out of 100 |
| 3 | verlReinforcement learning training library for LLM post-training with PPO and GRPO | 84 out of 100 |
| #4 | peftPython library for LoRA and other parameter-efficient fine-tuning of Transformers models | 84 out of 100 |
| #5 | trlPost-training library with SFT, DPO, GRPO and KTO trainers | 81 out of 100 |