ylcao
This appears to be due to insufficient memory: #2324
I had a similar situation: there was still a lot of unused memory. I'm guessing it has something to do with mode selection strategy? I wonder if there's a solution.
@igorschlum I have 36GB memory. ollama uses pure cpu calculations when I run the 70b 4bit model, and the speed is around 20-30 seconds per token. I tried to run...
已添加 [https://github.com/Le0nsec/SecCrawler/pull/26](https://github.com/Le0nsec/SecCrawler/pull/26)
I have another similar issue (simulating x86 programs on m3pro) terminal output: `[1] 15538 bus error sudo python3.13 ./fibonacci.py` report: ```plaintext ------------------------------------- Translated Report (Full Report Below) ------------------------------------- Process: Python...