James

@dmikushin Thanks Dmitry, I did some research and found this [implementation of BLAKE3 in cuda](https://github.com/Blaze-3/BLAKE3-gpu) which seems interesting. Maybe it would be faster than what I'm doing here. I was...

Apologies, I've run out of time to work on this. Please feel free to unlock and let others try. Here's results on Mac M2 GPU=1 | Input Size | Throughput...

Hey thanks for bringing this to my attention. I won’t be able to fix it unfortunately, I’m too busy with other things, but if someone wants to make a PR...

https://github.com/stanford-futuredata/ColBERT/issues/349 related, i posted a quick workaround

From Jake: ## Current Understanding - Issue 348 requests a way for agents to monitor and optionally interrupt long-running commands. - The `execute_shell` function in `gptme/tools/shell.py` is the main entry...

I got it kinda working with swe-agent and this dataset which contains many more issues: https://huggingface.co/datasets/nebius/SWE-bench-extra Might also integrate https://swe-rex.com/latest/ which seems pretty useful My branch is a giant mess...

I'll try to get back on this soon! At the very least I'll just share a gist which shows how to get the deps to install properly etc.

Hey sorry about that, I’m super busy atm and don’t have time to take a look, but if someone wants to make a PR I’ll gladly merge! On Tue, 8...

I was using the branch system to save each step in the understand, reproduce, fix cycle separately so I could restore from checkpoints

@ErikBjare I didn't do extensive testing, but it seemed to work pretty well. I didn't notice any bugs.