Tai-Pham-2002 comments

Repositories
Issues
Comments

Results 1 comments of


                                            Tai-Pham-2002

ollama can't run qwen:72b, error msg ""gpu VRAM usage didn't recover within timeout

when i run: ollama run aiden_lu/minicpm-v2.6:Q4_K_M got this error: Error: llama runner process has terminated: GGML_ASSERT(new_clip->has_llava_projector) failed this my log: Aug 29 17:35:21 ai-stg ollama[777926]: time=2024-08-29T17:35:21.555Z level=ERROR source=sched.go:456 msg="error loading...