microsoft / microsoft/TransformerCompression
Speed up test
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 460
- Forks
- 58
- Avg merge
- 8h 40m
- Merged PRs (30d)
- 1
Description
Hi,
Wonderful work u've done.
Some Q about the speed up for the structure pruning.
Actually, I pruned a llama2-7b into 0.3 sparsity, and test the forward time. Strangely, it cost more time to complete the forward time.
And then I test the attention forward and the feed forward then, the time consuming is below
first is the dense model, later is the 0.3 sparsity model, it takes more time to ffn,
don't u have this problem?
then I test on the next toy
so strange about my server!
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
The issue mentions no files, tests, or entry points. Start by reproducing the dense-versus-pruned forward-time comparison and document the model, environment, pruning configuration, and benchmark method; done should identify whether the slowdown is expected or reveal a reproducible performance defect.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100