31 lines
1.4 KiB
Markdown
31 lines
1.4 KiB
Markdown
## Salka Elmadani
|
||
|
||
**Building [Inference-X](https://inference-x.com)** — better output from the same model.
|
||
|
||
Universal AI inference engine. Fused computation, adaptive precision, surgical expert loading. 305 KB, 19 backends, zero dependencies. Built in Morocco.
|
||
|
||
### What I'm working on
|
||
|
||
| Project | Description |
|
||
|---------|-------------|
|
||
| [**Inference-X**](https://github.com/ElmadaniS/inference-x) | Universal inference engine — 305 KB binary, fused dequant+dot kernels, Shannon entropy adaptive precision, 23 quantization formats, 19 hardware backends |
|
||
| **Solar Inference** | Deploying AI on direct solar current. Adaptive precision + 25W power budget = inference powered by a star. Anti-Atlas, 2026. |
|
||
|
||
### Philosophy
|
||
|
||
> *The best inference engine is the one you don't notice. You should hear the model, not the framework.*
|
||
|
||
### How it works
|
||
|
||
The same model produces higher-fidelity output through Inference-X because the computation path is cleaner: fused kernels eliminate intermediate buffers, adaptive precision allocates depth where it matters, and surgical expert loading keeps only active parameters in memory.
|
||
|
||
→ [Full technical explanation](https://github.com/ElmadaniS/inference-x/blob/master/TECHNOLOGY.md)
|
||
|
||
### Links
|
||
|
||
🌐 [inference-x.com](https://inference-x.com) · 📧 [Elmadani.SALKA@proton.me](mailto:Elmadani.SALKA@proton.me) · 𝕏 [@ElmadaniSa13111](https://x.com/ElmadaniSa13111)
|
||
|
||
---
|
||
|
||
*Morocco 🇲🇦*
|