yu3zhou4
- Karma
- 1,281
- Created
- 4 years ago
About
Hello to you, person, AI, bot or perhaps another kind of being I haven’t identify yet. Here are some links to follow if you have some more time to spendhttps://github.com/jmaczan
https://jedrzej.maczan.pl
https://x.com/jedmaczan
jedrzej@maczan.pl
Wishing you a good day (or whatever timescale you operate on!)
Recent Submissions
- 1. ▲ Exapunks (2018) (zachtronics.com)
- 2. ▲ William Thurston: On Proof and Progress in Mathematics (1994) [pdf] (ams.org)
- 3. ▲ AMD contributes their GPU support to tiny-vLLM (github.com)
- 4. ▲ The Cypherpunk Library (cypherpunkbooks.com)
- 5. ▲ Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA (github.com)
- 6. ▲ TorchWebGPU: Running PyTorch Natively on WebGPU (github.com)
- 7. ▲ Ask HN: Did Claude lowered its usage limits?
- 8. ▲ Benchmark LLM Inference on WebGPU (arxiv.org)
- 9. ▲ Show HN: WebGPU LLM inference comprehensive benchmark (arxiv.org)