Günter
Günter
**With all the experimentation I have done over the last two weeks, after hours of comparison I found out that `pip install -e .` is the problem.** After several days...
As it would be my 1st pull request, I'll rather file a description here. Until yesterday I had inference only CPU-only running with Ubuntu 24.04 on my 256GB Xeon 2...
Didn't expect that such a nano-demo would require an Nvidia GPU > 20 series and Linux (WSL) for Triton. Didn't read far /deep (pyproject.toml) enough, so I bumped into the...
re [DGX Spark + Mac M3 Ultra](https://blog.exolabs.net/nvidia-dgx-spark/) 1. Why eth 10 Gb, not USB/TB 40Gb+ firstplace for max headroom? 2. Why DGX Spark, not low VRAM (not enough for prefill)...