支持在 H800上跑 int8 weight only 吗？
Open
- Dominant language
- Python
- Stars
- 1.3k
- Forks
- 275
- Avg merge
- 3d 17h
- Merged PRs (30d)
- 33
Description
如题
Contributor guide
No contributing guide indexed for this repository
Research direction
No files, tests, or entry points are identified in the issue. Start by locating the existing weight-only INT8 quantization and H800-related backend support, then determine the required implementation and validation path. Done means INT8 weight-only inference is demonstrably supported on H800 with an appropriate test or benchmark.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, backend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100