AIPython★ 53⑂ 7 forksApache-2.0
inclusionAI/ASpec
Speculative Decoding Training Framework
ASpec accelerates LLM inference by training efficient draft models for speculative decoding with high-throughput distributed training.
// KEY FEATURES
- Trains draft models for speculative decoding acceleration
- Supports multi-GPU distributed training with optimized throughput
- Integrates with Hugging Face Transformers and popular LLM architectures
#dflash#dflash2#dspark#eagle3#eagle4#ling-3#ling-3-flash#llm#mooncake#pytorch#sglang#speculative-decoding
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram