kvcache-ai / kvcache-ai/ktransformers
启动AMX功能报错
Open
- Dominant language
- Python
- Stars
- 19.5k
- Forks
- 1.6k
- Avg merge
- 19h 32m
- Merged PRs (30d)
- 27
Description
在启动local_chat 命令 --optimize_config_path ./....../optimize_rules/DeepSeek-V3-Chat-amx.yaml时报错，在开始部署专家层时显示精度转换问题，请问该如何解决
Contributor guide
Research direction
Reproduce the failure with the `local_chat` command and `--optimize_config_path` pointing to `optimize_rules/DeepSeek-V3-Chat-amx.yaml`. Start by reading the precision-conversion error shown in the attached image and tracing the expert-layer deployment path. Done means AMX startup completes without the reported precision-conversion failure.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100