Ryan Landay

Intermittent segmentation faults in llama_sample_top_p_top_k()

4

# Expected Behavior I have been getting intermittent segfaults for no apparent reason. Sometimes they occur right at the beginning of text generation, and sometimes they occur after a lot...

# Expected Behavior I was previously mostly using the 65B LLaMA model to generate text (I have 64 GB of RAM) and expected to be able to continue doing that....

TypeError: Input tensors need to be on the same GPU, but found the following tensor and device combinations

6

### System Info I was using a Vast.ai server with 8x A100 GPUs, each with 80 GB of VRAM, and about 1814 GB of RAM (as reported by Vast): ```...

“ld: symbol(s) not found for architecture x86_64” when installing 3.14t-dev over a previous snapshot

9

Note that this issue is listed on the “Common build problems” page: https://github.com/pyenv/pyenv/wiki/Common-build-problems#macos-ld-symbols-not-found-for-architecture-x86_64-1245 However, I tried running “brew remove binutils” and it said it’s not installed. Also, compiling and installing...

sl pull hangs on sapling.ext.github.pr_marker.cleanup_landed_pr_hook

1

I cloned a GitHub repo using “git clone ” (so VS Code could show me blame, which didn’t work when I used “sl clone”) and ran into a problem where...