|
|
||
|---|---|---|
| .. | ||
| EAGLE | ||
| Self-Speculation | ||
| README.md | ||
Speculative-Decoding Examples on Intel CPU
This folder contains examples of running Speculative-Decoding Examples with IPEX-LLM on Intel CPU:
- Self-Speculation: running BF16 inference for Huggingface Transformer model with self-speculative decoding with IPEX-LLM on Intel CPUs
- EAGLE: running speculative sampling using EAGLE (Extrapolation Algorithm for Greater Language-model Efficiency) with IPEX-LLM on Intel CPUs