Capyun

Results 12 comments of Capyun

[Speed] MLC is much slower than Ollama when running Qwen Coder 30b

> I have a very strange situation with MLC LLM. Tested on qwen3-14b_q4f16 When I increase the input token length request up to 1500-2500tokens then the MLC load my CPU...

jetson-containers build nanollm results in "couldn't find package: flash-attention"

I get this error too.