xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 02:05:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Doc]Add documentation for using EAGLE in vLLM (#11417)

Browse Source 
Signed-off-by: Sourashis Roy <sroy@roblox.com>
This commit is contained in:
sroy745 2025-01-07 11:19:12 -08:00 committed by GitHub
parent c994223d56
commit 973f5dc581
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 66 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
docs/source/features/spec_decode.md
View File

@ -159,6 +159,72 @@ A variety of speculative models of this type are available on HF hub:
- [granite-7b-instruct-accelerator](https://huggingface.co/ibm-granite/granite-7b-instruct-accelerator) - [granite-7b-instruct-accelerator](https://huggingface.co/ibm-granite/granite-7b-instruct-accelerator)
- [granite-20b-code-instruct-accelerator](https://huggingface.co/ibm-granite/granite-20b-code-instruct-accelerator) - [granite-20b-code-instruct-accelerator](https://huggingface.co/ibm-granite/granite-20b-code-instruct-accelerator)
## Speculating using EAGLE based draft models
The following code configures vLLM to use speculative decoding where proposals are generated by
an [EAGLE (Extrapolation Algorithm for Greater Language-model Efficiency)](https://arxiv.org/pdf/2401.15077) based draft model.
```python
from vllm import LLM, SamplingParams
prompts = [
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(
model="meta-llama/Meta-Llama-3-8B-Instruct",
tensor_parallel_size=4,
speculative_model="path/to/modified/eagle/model",
speculative_draft_tensor_parallel_size=1,
)
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
A few important things to consider when using the EAGLE based draft models:
1. The EAGLE draft models available in the [HF repository for EAGLE models](https://huggingface.co/yuhuili) cannot be
used directly with vLLM due to differences in the expected layer names and model definition.
To use these models with vLLM, use the [following script](https://gist.github.com/abhigoyal1997/1e7a4109ccb7704fbc67f625e86b2d6d)
to convert them. Note that this script does not modify the model's weights.
In the above example, use the script to first convert
the [yuhuili/EAGLE-LLaMA3-Instruct-8B](https://huggingface.co/yuhuili/EAGLE-LLaMA3-Instruct-8B) model
and then use the converted checkpoint as the draft model in vLLM.
2. The EAGLE based draft models need to be run without tensor parallelism
(i.e. speculative_draft_tensor_parallel_size is set to 1), although
it is possible to run the main model using tensor parallelism (see example above).
3. When using EAGLE-based speculators with vLLM, the observed speedup is lower than what is
reported in the reference implementation [here](https://github.com/SafeAILab/EAGLE). This issue is under
investigation and tracked here: [https://github.com/vllm-project/vllm/issues/9565](https://github.com/vllm-project/vllm/issues/9565).
A variety of EAGLE draft models are available on the Hugging Face hub:
| Base Model | EAGLE on Hugging Face | # EAGLE Parameters |
|---------------------------------------------------------------------|-------------------------------------------|--------------------|
| Vicuna-7B-v1.3 | yuhuili/EAGLE-Vicuna-7B-v1.3 | 0.24B |
| Vicuna-13B-v1.3 | yuhuili/EAGLE-Vicuna-13B-v1.3 | 0.37B |
| Vicuna-33B-v1.3 | yuhuili/EAGLE-Vicuna-33B-v1.3 | 0.56B |
| LLaMA2-Chat 7B | yuhuili/EAGLE-llama2-chat-7B | 0.24B |
| LLaMA2-Chat 13B | yuhuili/EAGLE-llama2-chat-13B | 0.37B |
| LLaMA2-Chat 70B | yuhuili/EAGLE-llama2-chat-70B | 0.99B |
| Mixtral-8x7B-Instruct-v0.1 | yuhuili/EAGLE-mixtral-instruct-8x7B | 0.28B |
| LLaMA3-Instruct 8B | yuhuili/EAGLE-LLaMA3-Instruct-8B | 0.25B |
| LLaMA3-Instruct 70B | yuhuili/EAGLE-LLaMA3-Instruct-70B | 0.99B |
| Qwen2-7B-Instruct | yuhuili/EAGLE-Qwen2-7B-Instruct | 0.26B |
| Qwen2-72B-Instruct | yuhuili/EAGLE-Qwen2-72B-Instruct | 1.05B |
## Lossless guarantees of Speculative Decoding ## Lossless guarantees of Speculative Decoding
In vLLM, speculative decoding aims to enhance inference efficiency while maintaining accuracy. This section addresses the lossless guarantees of In vLLM, speculative decoding aims to enhance inference efficiency while maintaining accuracy. This section addresses the lossless guarantees of