microsoft / microsoft/MInference
[Question]: How to use quantification and MInference together
Open
Nobody has claimed this yet.
question
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 82
- Avg merge
- 1d 18h
- Merged PRs (30d)
- 1
Description
Describe the issue
Thank you for your work. I’m quite curious about how the current approach (flexPrefill / triangle attention) can be used alongside quantization (fp8/int8/fp4) in vLLM/trt-llm, since quantization provides a very significant speedup in our scenario. Thank you! @iofu728
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
No files, tests, or entry points are named. Start by reviewing the current flexPrefill and triangle attention usage alongside quantization in vLLM and trt-llm; the issue would be done when compatibility and usage guidance for fp8, int8, or fp4 is documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100