EAGLE support and examples

[jeanyu-habana]

Description

ipex-llm and EAGLE integration plus EAGLE example scripts

1. Why the change?

EAGLE provides significant speedup in addition to ipex-llm optimizations. Please see below:
Llama 7B, temporature=1.0, Intel CPU
speed 27.445331381249126 TPS (optimized with both EAGLE and ipex-llm)
speed 20.132597255230788 TPS (optimized with EAGLE only)
speed 14.549053180428723 TPS (optimized with ipex-llm only)
speed_base 10.275284471199816 TPS (Baseline: not optimized)

Llama 7B, temporature=1.0, Intel GPU
speed 60.68802901159256 TPS eagle + ipex-llm (ratio: 3.74)
speed 41.41260508527679 TPS ipex-llm only (ratio: 2.55)
speed 31.480931699222744 TPS eagle only (ratio: 1.94)
speed_base 16.220403337894584 TPS (Baseline: not optimized)

2. User API changes

N/A

3. Summary of the change

Integrate with EAGLE (https://github.com/SafeAILab/EAGLE) and provide examples

4. How to test?

• N/A
• Unit test
• [ X] Application test
• Document test
• ...
  Please follow the setup instructions and example commands in the README.

[jenniew]

I suggest you to put examples under ipex-llm/python/llm/example/CPU/PyTorch-Models and ipex-llm/python/llm/example/GPU/PyTorch-Models

[jenniew]

@jason-dai For the Eagle example placement, which directory is best to put to? like ipex-llm/python/llm/example/CPU/PyTorch-Models/EAGLE or ipex-llm/python/llm/example/CPU/Speculative-Decoding/EAGLE? If we put eagle example to ipex-llm/python/llm/example/CPU/Speculative-Decoding, we may need to create a new directory, like ipex-llm/python/llm/example/CPU/Speculative-Decoding/ipex-llm, and move our current speculative examples to that directory.

[jason-dai]

@jason-dai For the Eagle example placement, which directory is best to put to? like ipex-llm/python/llm/example/CPU/PyTorch-Models/EAGLE or ipex-llm/python/llm/example/CPU/Speculative-Decoding/EAGLE? If we put eagle example to ipex-llm/python/llm/example/CPU/Speculative-Decoding, we may need to create a new directory, like ipex-llm/python/llm/example/CPU/Speculative-Decoding/ipex-llm, and move our current speculative examples to that directory.

Maybe example/CPU/Speculative-Decoding with Self-Speculation and Eagle folders

[jeanyu-habana]

After discussing with @jenniew , we agreed to use a new PR for a cleaner merge : #11104. For this reason, I am closing this PR