what's the decode token speed of 7b qwen gptq int4 model on v100?
Open
- Dominant language
- Python
- Stars
- 1.3k
- Forks
- 275
- Avg merge
- 3d 17h
- Merged PRs (30d)
- 33
Description
how about the compre with vllm? thx!
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by identifying the repository entry points for running a 7B Qwen GPTQ INT4 model on a V100, then determine how decode-token speed is measured. Compare the result with vLLM under equivalent conditions and document the measurements and test setup; the issue is complete when both speeds are reported clearly.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, performance
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100