2624 segmentation fault tabby serve

[mindaslab]

Describe the bug Getting segmentation fault while running tabby

 ~ tabby serve --device metal --model StarCoder-1B --chat-model Qwen2-1.5B-Instruct
🔑 Parsed .netrc from: .netrc
Writing to new file.
🎯 Downloaded https://huggingface.co/Qwen/Qwen2-1.5B-Instruct-GGUF/resolve/main/qwen2-1_5b-instruct-q8_0.gguf to /Users/karthik/.tabby/models/TabbyML/Qwen2-1.5B-Instruct/ggml/model.gguf.tmp
   00:11:29 ▕████████████████████▏ 1.53 GiB/1.53 GiB  2.28 MiB/s  ETA 0s.                                                                                                                                                                                                                           ✅ Checksum OK.
🔑 Parsed .netrc from: .netrc
Writing to new file.
🎯 Downloaded https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF/resolve/main/nomic-embed-text-v1.5.Q8_0.gguf to /Users/karthik/.tabby/models/TabbyML/Nomic-Embed-Text/ggml/model.gguf.tmp
   00:01:19 ▕████████████████████▏ 139.38 MiB/139.38 MiB  1.75 MiB/s  ETA 0s.                                                                                                                                                                                                                       ✅ Checksum OK.
⠧    22.600 s   Starting...[1]    2624 segmentation fault  tabby serve --device metal --model StarCoder-1B --chat-model

Information about your version

 ~ tabby --version
tabby 0.16.1

Information about your GPU

~ nvidia-smi
zsh: command not found: nvidia-smi

I run on Mac M1

Additional context

Applw M1 Pro, OS: Sonoma 14.6.1

[wsxiaoys]

Thanks for reporting the issue.

Could you turn on RUST_LOG=debug and share a log trace?

[mindaslab]

~ RUST_LOG=debug  tabby serve --device metal --model StarCoder-1B --chat-model Qwen2-1.5B-Instruct > tabby_segmentation_fault.txt

tabby_segmentation_fault.txt

@wsxiaoys Please find the file attached. Thank you.