salka/ElmadaniS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update profile — signal quality, adaptive precision, fused computation

Browse Source
This commit is contained in:
Salka Elmadani 2026-02-23 06:51:35 +00:00
parent dc1ad70a4e
commit 64727ec35d
1 changed files with 12 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@ -1,23 +1,29 @@
## Salka Elmadani
**Building [Inference-X](https://inference-x.com)** — the shortest path between a model and silicon.
**Building [Inference-X](https://inference-x.com)** — better output from the same model.
One binary routes any AI model to any hardware. 305 KB. 19 backends. Zero dependencies. Built in Morocco.
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 protocol — 305 KB, C++17, 23 quantization formats, 19 hardware backends |
| **Solar Inference** | Running AI on direct current from solar panels. No cloud. No API key. Just starlight. |
| [**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
> *In the Anti-Atlas, our ancestors built khettaras — underground water channels that irrigate villages without pumps, without electricity, flowing for centuries by gravity alone. Inference-X is the khettara of intelligence: once built, it flows without intervention.*
> *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) · 🐦 [@ElmadaniSa13111](https://x.com/ElmadaniSa13111)
🌐 [inference-x.com](https://inference-x.com) · 📧 [Elmadani.SALKA@proton.me](mailto:Elmadani.SALKA@proton.me) · 𝕏 [@ElmadaniSa13111](https://x.com/ElmadaniSa13111)
---