simoiacos
Joined 2 years ago
Karma
20
Submissions
7
Member since
May 27
Recent submissions
Comment · 1 month ago
Thank you, appreciate it!
Comment · 1 month ago
I just added experimental support for Xe-LPG and Xe-LPG+ in main so you should be able to try it without a patch now.
As I said, I don't have the hardware to test it myself, so let me know how it goes!
Comment · 1 month ago
Please open a PR! I was too conservative with the supported devices.
If your GPU supports XMX we could also explore using it to improve the prefill kernel, but I don't have the hardware to test it myself.
Comment · 1 month ago
He recently said that he finds Rust less ergonomic and that this also affects code written by LLMs, which he thinks excel at writing C partly because of the enormous, high-quality codebase they were trained on. He sees security-critical code as a reason to choose Rust.
The video is in Italian but has an auto-dubbed English audio track: https://www.youtube.com/watch?v=sOt0WpQG5eU\&t=526s
Comment · 1 month ago
Yeah I see the value but I built Xenolith to target smaller models.
I heard antirez saying that he designed DwarfStar also to be forked and tuned to everyone's specific needs. Do you have a specific machine/spec in mind?
Comment · 1 month ago
Nothing comparable but inspired from DwarfStar I wrote a little inference engine for Intel Xe-LP (no XMX) 32GB laptops. The only model supported right now is a quantized Gemma-4, but I don't exclude in the future to support other MoE of similar size. Too bad we have no Qwen 3.8 35B-A3B yet.
I'm also looking into expanding the protocol and the engine to support various steering techniques.
Comment · 9 months ago
Really cute game, nice work!