speculative-decoding-lab
新上架免费
Hands-on lab for implementing, benchmarking, and comparing speculative decoding across from-scratch, Hugging Face, and vLLM implementations, with reproducible GPU performance benchmarks.
相关标签
generative-ai
huggingface
llm-inference
llm-inference-optimization
speculative-decoding
ai
ai assistant
automation
用户评论
还没有评论，来分享你的使用体验吧