deepspeedai / deepspeedai/DeepSpeedExamples
Question to attention computation
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 6.8k
- Forks
- 1.1k
- Avg merge
- 2d 16h
- Merged PRs (30d)
- 1
Description
Hi, thank you for the amazing demo and doc! I have a question regarding this section in zero-inference. It is mentioned that "Thus, our current implementation computes attention scores on CPU". May I ask if there is a detailed comparison of the latency or throughput between GPU-attention and CPU-attention to support this desicion? I am also serious about the implementation detail of the CPU-attention computation. Thank you!
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with inference/huggingface/zero_inference/model-support.md, especially section 5, and investigate the implementation details of the CPU attention computation referenced there. Determine whether a GPU-versus-CPU latency or throughput comparison and a detailed explanation can be added to answer the question.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100