forked from elmadani/inference-x
Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
7e93ca5a70 | ||
|
|
22a945d07c | ||
|
|
dce92e0808 | ||
|
|
cc6c404898 | ||
|
|
4295295753 | ||
|
|
e2bb3b8bdd | ||
|
|
781bf6ba80 |
@ -51,7 +51,6 @@ Every design decision serves two goals: route intelligence to any hardware, and
|
|||||||
|---|---|---|
|
|---|---|---|
|
||||||
| `infer.cpp` | ~570 | Entry point, CLI, mode dispatch |
|
| `infer.cpp` | ~570 | Entry point, CLI, mode dispatch |
|
||||||
| `runtime/server.h` | ~530 | OpenAI-compatible HTTP API, SSE streaming |
|
| `runtime/server.h` | ~530 | OpenAI-compatible HTTP API, SSE streaming |
|
||||||
| `runtime/fractal.h` | ~320 | Dynamic precision per layer (fractal inference) |
|
|
||||||
| `runtime/identity.h` | ~160 | Cryptographic authorship, 4-layer protection |
|
| `runtime/identity.h` | ~160 | Cryptographic authorship, 4-layer protection |
|
||||||
|
|
||||||
### Compute Layer
|
### Compute Layer
|
||||||
@ -103,7 +102,6 @@ Expert mmap loads only active experts via memory-mapped files with predictive pr
|
|||||||
|
|
||||||
Result: 48× I/O reduction for trillion-parameter models. The signal path contains only parameters that contribute to the current answer. Nothing else exists in memory.
|
Result: 48× I/O reduction for trillion-parameter models. The signal path contains only parameters that contribute to the current answer. Nothing else exists in memory.
|
||||||
|
|
||||||
### Fractal Inference (Adaptive Precision)
|
|
||||||
|
|
||||||
Query complexity determines layer precision. Shannon entropy of input tokens + vocabulary diversity → composite complexity score → per-layer quantization map.
|
Query complexity determines layer precision. Shannon entropy of input tokens + vocabulary diversity → composite complexity score → per-layer quantization map.
|
||||||
|
|
||||||
|
|||||||
@ -2,7 +2,7 @@
|
|||||||
|
|
||||||
## Creator & Lead Developer
|
## Creator & Lead Developer
|
||||||
- **Salka Elmadani** — Architecture, implementation, and all original code
|
- **Salka Elmadani** — Architecture, implementation, and all original code
|
||||||
- GitHub: [@ElmadaniS](https://git.inference-x.com/salka)
|
- Git: [@elmadani](https://git.inference-x.com/elmadani)
|
||||||
- Email: Elmadani.SALKA@proton.me
|
- Email: Elmadani.SALKA@proton.me
|
||||||
|
|
||||||
## Infrastructure Partners
|
## Infrastructure Partners
|
||||||
|
|||||||
1
Makefile
1
Makefile
@ -48,7 +48,6 @@ endif
|
|||||||
# 2. Sets IX_USE_* define
|
# 2. Sets IX_USE_* define
|
||||||
# 3. Adds the backend .c/.cpp to BACKEND_OBJS
|
# 3. Adds the backend .c/.cpp to BACKEND_OBJS
|
||||||
# 4. Adds SDK-specific link flags
|
# 4. Adds SDK-specific link flags
|
||||||
#
|
|
||||||
# Without SDK → nothing happens. Zero noise.
|
# Without SDK → nothing happens. Zero noise.
|
||||||
# ──────────────────────────────────────────────────────────────────────────────
|
# ──────────────────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
|||||||
@ -8,7 +8,7 @@
|
|||||||
|
|
||||||
Inference-X is a tiny file (305 KB) that lets any computer run AI models locally. It works on old laptops, phones, Raspberry Pi, and datacenters — same file, no setup. Your questions stay on your machine. Nobody sees them.
|
Inference-X is a tiny file (305 KB) that lets any computer run AI models locally. It works on old laptops, phones, Raspberry Pi, and datacenters — same file, no setup. Your questions stay on your machine. Nobody sees them.
|
||||||
|
|
||||||
**[Website](https://inference-x.com)** · **[How it works](TECHNOLOGY.md)** · **[Benchmarks](BENCHMARKS.md)** · **[Vision](VISION.md)** · **[Sponsor](https://git.inference-x.com/salka)**
|
**[Website](https://inference-x.com)** · **[How it works](TECHNOLOGY.md)** · **[Benchmarks](BENCHMARKS.md)** · **[Vision](VISION.md)** · **[Sponsor](SPONSOR.md)**
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
@ -193,4 +193,4 @@ Built in Morocco for the world by [Salka Elmadani](https://x.com/ElmadaniSa13111
|
|||||||
|
|
||||||
> *The shortest path between model weights and output produces the cleanest signal. Every buffer removed, every conversion eliminated, every unnecessary step subtracted — each one brings the output closer to what the model actually learned. The path itself is the filter.*
|
> *The shortest path between model weights and output produces the cleanest signal. Every buffer removed, every conversion eliminated, every unnecessary step subtracted — each one brings the output closer to what the model actually learned. The path itself is the filter.*
|
||||||
|
|
||||||
**[Website](https://inference-x.com)** · **[Sponsor](https://git.inference-x.com/salka)** · **[Contact](mailto:Elmadani.SALKA@proton.me)**
|
**[Website](https://inference-x.com)** · **[Sponsor](SPONSOR.md)** · **[Contact](mailto:Elmadani.SALKA@proton.me)**
|
||||||
|
|||||||
123
SPONSOR.md
Normal file
123
SPONSOR.md
Normal file
@ -0,0 +1,123 @@
|
|||||||
|
# Salka Elmadani — Building Inference-X
|
||||||
|
|
||||||
|
> *The best engine is the one you don't notice.*
|
||||||
|
> *You should hear the model, not the framework.*
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
|
||||||
|
I build AI infrastructure. Not products, not demos, not wrappers around someone else's API. Infrastructure — the kind that runs without permission, works without cloud, and belongs to anyone who needs it.
|
||||||
|
|
||||||
|
**Inference-X** is a 305 KB binary that runs any AI model on any hardware. No framework. No internet. No account. Download a model, run it, talk to it. That's it.
|
||||||
|
|
||||||
|
I built it alone. I'm still building it alone. This page is why.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What I'm building
|
||||||
|
|
||||||
|
The problem isn't the models. The models are extraordinary. The problem is the layer between the weights and the human — the inference stack. It's bloated, cloud-dependent, and controlled by a handful of companies.
|
||||||
|
|
||||||
|
I'm replacing that layer with something minimal, open, and community-owned.
|
||||||
|
|
||||||
|
```
|
||||||
|
Standard engine path:
|
||||||
|
weights → framework → dequant buffer → matmul → buffer → output
|
||||||
|
~100 MB binary. 5 steps. Rounding errors at each boundary.
|
||||||
|
|
||||||
|
Inference-X:
|
||||||
|
weights → fused dequant+dot → output
|
||||||
|
305 KB binary. 2 steps. Zero buffer. Zero noise.
|
||||||
|
```
|
||||||
|
|
||||||
|
Same model. Cleaner signal. Every unnecessary step removed.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## The ecosystem
|
||||||
|
|
||||||
|
| Project | What it does | Status |
|
||||||
|
|---------|-------------|--------|
|
||||||
|
| **[inference-x](https://git.inference-x.com/elmadani/inference-x)** | Core engine — 305 KB, 19 hardware backends, 23 quant formats, fused kernels, adaptive precision | ✅ Live |
|
||||||
|
| **forge** | Model construction pipeline — compile, quantize, sign, distribute. Build your own model variant from certified organs. | 🔨 Building |
|
||||||
|
| **[echo-ix](https://git.inference-x.com/elmadani/echo-ix)** | Distributed relay — intelligent routing across local inference nodes | ✅ Live |
|
||||||
|
| **store** | Anyone deploys a node. Anyone earns from their compute. The cooperative layer. 11 geological cratons. One network. | 📐 Designed |
|
||||||
|
|
||||||
|
The store is the endgame: a peer-to-peer inference network where anyone with a laptop can become infrastructure. No data center required.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
The intelligence already exists in the model weights. What I'm building is the canal — the shortest, cleanest path from those weights to the human who needs them.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Who this is free for
|
||||||
|
|
||||||
|
**Everyone who isn't extracting commercial value from it:**
|
||||||
|
|
||||||
|
- Individuals and researchers — forever free
|
||||||
|
- Students — forever free
|
||||||
|
- Open-source projects — forever free
|
||||||
|
- Organizations under $1M revenue — forever free
|
||||||
|
|
||||||
|
**Commercial users above $1M revenue** pay a license. 20% of that flows back to the community that built the infrastructure.
|
||||||
|
|
||||||
|
In 2030, it all becomes Apache 2.0. Everything open. The canal belongs to everyone.
|
||||||
|
|
||||||
|
This isn't charity. It's a sustainable model — those who profit from it fund it. Those who don't, use it freely.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Why I need support
|
||||||
|
|
||||||
|
Servers cost money. The current infrastructure — [inference-x.com](https://inference-x.com), [build.inference-x.com](https://build.inference-x.com), [git.inference-x.com](https://git.inference-x.com) — runs on €53/month.
|
||||||
|
|
||||||
|
More importantly: time. The engine, the organ pipeline, the forge tools, the store architecture — this is one engineer, building in the margins of everything else.
|
||||||
|
|
||||||
|
There is no team. No VC. No roadmap driven by investor pressure.
|
||||||
|
|
||||||
|
There is one person who decided this infrastructure should exist.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## How to help
|
||||||
|
|
||||||
|
### Build with me
|
||||||
|
|
||||||
|
The most valuable contribution is code. The project is open, the roadmap is public, and good engineers are always welcome.
|
||||||
|
|
||||||
|
**→ Pick a task**: [git.inference-x.com/elmadani/inference-x](https://git.inference-x.com/elmadani/inference-x)
|
||||||
|
**→ Administer a craton**: Each of the 11 community regions needs a technical lead. Write to [Elmadani.SALKA@proton.me](mailto:Elmadani.SALKA@proton.me) — subject: `Craton — [your region]`
|
||||||
|
|
||||||
|
### Sustain the infrastructure
|
||||||
|
|
||||||
|
**PayPal** → [paypal.me/elmadanisalka](https://paypal.me/elmadanisalka)
|
||||||
|
|
||||||
|
€5 = one day of server time. €53 = one month of everything running.
|
||||||
|
|
||||||
|
### Amplify
|
||||||
|
|
||||||
|
Every post that reaches a developer who cares about AI sovereignty is one more person who might build the next piece.
|
||||||
|
|
||||||
|
**→ [Follow on X: @ElmadaniSa13111](https://x.com/ElmadaniSa13111)**
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Contact
|
||||||
|
|
||||||
|
I respond to everyone who writes with something real to say.
|
||||||
|
|
||||||
|
| | |
|
||||||
|
|--|--|
|
||||||
|
| **X** | [@ElmadaniSa13111](https://x.com/ElmadaniSa13111) — fastest response |
|
||||||
|
| **Email** | [Elmadani.SALKA@proton.me](mailto:Elmadani.SALKA@proton.me) — for technical discussions, partnerships, craton applications |
|
||||||
|
| **Code** | [@elmadani on Gitea](https://git.inference-x.com/elmadani) |
|
||||||
|
| **Web** | [inference-x.com](https://inference-x.com) |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
*Morocco → the world.*
|
||||||
|
*Salka Elmadani, 2024–2026*
|
||||||
@ -181,7 +181,7 @@ Kimi K2.5 on Inference-X:
|
|||||||
## Try it
|
## Try it
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
git clone https://git.inference-x.com/salka/inference-x
|
git clone https://git.inference-x.com/elmadani/inference-x
|
||||||
cd inference-x
|
cd inference-x
|
||||||
make
|
make
|
||||||
./inference-x model.gguf -p "Hello"
|
./inference-x model.gguf -p "Hello"
|
||||||
|
|||||||
@ -17,7 +17,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-CEREBRAS_WSE"
|
#define IX_BACKEND_ID "Inference-X-CEREBRAS_WSE"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: CEREBRAS_WSE | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: CEREBRAS_WSE | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -12,7 +12,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-FPGA_XILINX"
|
#define IX_BACKEND_ID "Inference-X-FPGA_XILINX"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: FPGA_XILINX | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: FPGA_XILINX | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -12,7 +12,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-GAUDI"
|
#define IX_BACKEND_ID "Inference-X-GAUDI"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: GAUDI | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: GAUDI | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -12,7 +12,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-GRAPHCORE_IPU"
|
#define IX_BACKEND_ID "Inference-X-GRAPHCORE_IPU"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: GRAPHCORE_IPU | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: GRAPHCORE_IPU | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -19,7 +19,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-GROQ_LPU"
|
#define IX_BACKEND_ID "Inference-X-GROQ_LPU"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: GROQ_LPU | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: GROQ_LPU | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -19,7 +19,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-HEXAGON"
|
#define IX_BACKEND_ID "Inference-X-HEXAGON"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: HEXAGON | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: HEXAGON | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -12,7 +12,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-AWS_INFERENTIA"
|
#define IX_BACKEND_ID "Inference-X-AWS_INFERENTIA"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: AWS_INFERENTIA | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: AWS_INFERENTIA | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -12,7 +12,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-MICROSOFT_MAIA"
|
#define IX_BACKEND_ID "Inference-X-MICROSOFT_MAIA"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: MICROSOFT_MAIA | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: MICROSOFT_MAIA | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -12,7 +12,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-SAMBANOVA_RDU"
|
#define IX_BACKEND_ID "Inference-X-SAMBANOVA_RDU"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: SAMBANOVA_RDU | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: SAMBANOVA_RDU | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -12,7 +12,6 @@
|
|||||||
|
|
||||||
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
// Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
#define IX_BACKEND_ID "Inference-X-SNAPDRAGON"
|
#define IX_BACKEND_ID "Inference-X-SNAPDRAGON"
|
||||||
#define IX_BACKEND_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
static void ix_backend_announce() {
|
static void ix_backend_announce() {
|
||||||
fprintf(stderr, "[Inference-X] Backend: SNAPDRAGON | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
fprintf(stderr, "[Inference-X] Backend: SNAPDRAGON | Author: Salka Elmadani | Author: Salka Elmadani\n");
|
||||||
|
|||||||
@ -3,7 +3,6 @@
|
|||||||
# Copyright (C) 2025-2026 Salka Elmadani. All rights reserved.
|
# Copyright (C) 2025-2026 Salka Elmadani. All rights reserved.
|
||||||
# Licensed under the Business Source License 1.1 (BSL-1.1)
|
# Licensed under the Business Source License 1.1 (BSL-1.1)
|
||||||
# See LICENSE file for full terms. See LICENSE for terms.
|
# See LICENSE file for full terms. See LICENSE for terms.
|
||||||
#
|
|
||||||
# NOTICE: This file is part of Inference-X by Salka Elmadani.
|
# NOTICE: This file is part of Inference-X by Salka Elmadani.
|
||||||
# Commercial use by entities with revenue >= $1M USD requires a license.
|
# Commercial use by entities with revenue >= $1M USD requires a license.
|
||||||
# Contact: Elmadani.SALKA@proton.me
|
# Contact: Elmadani.SALKA@proton.me
|
||||||
@ -12,7 +11,6 @@
|
|||||||
|
|
||||||
# Inference-X Backend Identity — Salka Elmadani — Morocco
|
# Inference-X Backend Identity — Salka Elmadani — Morocco
|
||||||
IX_BACKEND_ID = "Inference-X-GOOGLE_TPU"
|
IX_BACKEND_ID = "Inference-X-GOOGLE_TPU"
|
||||||
IX_BACKEND_FINGERPRINT = 0x935E1DAD
|
|
||||||
|
|
||||||
def ix_backend_announce():
|
def ix_backend_announce():
|
||||||
"""Announces this backend. Required by BSL-1.1."""
|
"""Announces this backend. Required by BSL-1.1."""
|
||||||
|
|||||||
@ -20,7 +20,6 @@
|
|||||||
// ═══════════════════════════════════════════════════════════════════════════════
|
// ═══════════════════════════════════════════════════════════════════════════════
|
||||||
|
|
||||||
#pragma once
|
#pragma once
|
||||||
#define IX_TABLES_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
#include <cstdint>
|
#include <cstdint>
|
||||||
|
|
||||||
|
|||||||
@ -20,7 +20,6 @@
|
|||||||
// ═══════════════════════════════════════════════════════════════════════════════
|
// ═══════════════════════════════════════════════════════════════════════════════
|
||||||
|
|
||||||
#pragma once
|
#pragma once
|
||||||
#define IX_TABLES_EXT_FINGERPRINT 0x935E1DAD
|
|
||||||
|
|
||||||
// INFERENCE-X v6 — Extended IQ Lookup Tables
|
// INFERENCE-X v6 — Extended IQ Lookup Tables
|
||||||
// COPYRIGHT (C) 2025-2026 SALKA ELMADANI — ALL RIGHTS RESERVED
|
// COPYRIGHT (C) 2025-2026 SALKA ELMADANI — ALL RIGHTS RESERVED
|
||||||
|
|||||||
@ -20,8 +20,6 @@
|
|||||||
// ═══════════════════════════════════════════════════════════════════════════════
|
// ═══════════════════════════════════════════════════════════════════════════════
|
||||||
|
|
||||||
#pragma once
|
#pragma once
|
||||||
#define IX_ZCORE_FINGERPRINT 0x935E1DAD
|
|
||||||
#define IX_ZCORE_MARK "Inference-X-ZCore-935-Elmadani"
|
|
||||||
|
|
||||||
|
|
||||||
#include <cstdint>
|
#include <cstdint>
|
||||||
@ -43,10 +41,10 @@ namespace ix {
|
|||||||
// WATERMARK — SALKA ELMADANI SIGNATURE (Ne pas modifier)
|
// WATERMARK — SALKA ELMADANI SIGNATURE (Ne pas modifier)
|
||||||
// ═══════════════════════════════════════════════════════════════════════════════
|
// ═══════════════════════════════════════════════════════════════════════════════
|
||||||
namespace signature {
|
namespace signature {
|
||||||
static constexpr double S0 = 5.999160064733103e+18; // "SALKA EL"
|
static constexpr double S0 = 5.999160064733103e+18; // Integrity coefficient α
|
||||||
static constexpr double S1 = 5.566805661683622e+18; // "MADANI E"
|
static constexpr double S1 = 5.566805661683622e+18; // Integrity coefficient β
|
||||||
static constexpr double S2 = 5.426309097159753e+18; // "LMADANI"
|
static constexpr double S2 = 5.426309097159753e+18; // Integrity coefficient γ
|
||||||
static constexpr double S3 = 4.991471925827590e+18; // "CREATOR"
|
static constexpr double S3 = 4.991471925827590e+18; // Integrity coefficient δ
|
||||||
|
|
||||||
inline bool verify() {
|
inline bool verify() {
|
||||||
volatile double sum = S0 + S1 + S2 + S3;
|
volatile double sum = S0 + S1 + S2 + S3;
|
||||||
@ -226,7 +224,7 @@ struct block_q8_1 {
|
|||||||
};
|
};
|
||||||
|
|
||||||
|
|
||||||
// Z-VERIFY: Block sizes must match GGUF binary format exactly
|
// STATIC ASSERT: Block sizes must match GGUF binary format exactly
|
||||||
static_assert(sizeof(block_q4_K) == 144, "block_q4_K size mismatch!");
|
static_assert(sizeof(block_q4_K) == 144, "block_q4_K size mismatch!");
|
||||||
static_assert(sizeof(block_q8_0) == 34, "block_q8_0 size mismatch!");
|
static_assert(sizeof(block_q8_0) == 34, "block_q8_0 size mismatch!");
|
||||||
static_assert(sizeof(block_q6_K) == 210, "block_q6_K size mismatch!");
|
static_assert(sizeof(block_q6_K) == 210, "block_q6_K size mismatch!");
|
||||||
|
|||||||
@ -31,7 +31,6 @@ static const char* IX_AUTHOR = "Salka Elmadani";
|
|||||||
static const char* IX_LICENSE __attribute__((unused)) = "BSL-1.1";
|
static const char* IX_LICENSE __attribute__((unused)) = "BSL-1.1";
|
||||||
static const char* IX_CONTACT __attribute__((unused)) = "Elmadani.SALKA@proton.me";
|
static const char* IX_CONTACT __attribute__((unused)) = "Elmadani.SALKA@proton.me";
|
||||||
static const char* IX_SIGNATURE = "IX";
|
static const char* IX_SIGNATURE = "IX";
|
||||||
static const uint32_t IX_FINGERPRINT = 0x935E1DAD; // Elmadani in hex
|
|
||||||
|
|
||||||
static void ix_print_banner() {
|
static void ix_print_banner() {
|
||||||
fprintf(stderr, "\n");
|
fprintf(stderr, "\n");
|
||||||
@ -47,7 +46,6 @@ static void ix_print_banner() {
|
|||||||
static bool ix_verify_integrity() {
|
static bool ix_verify_integrity() {
|
||||||
// Integrity check — fingerprint must match
|
// Integrity check — fingerprint must match
|
||||||
// Tampering with this function violates the license
|
// Tampering with this function violates the license
|
||||||
return (IX_FINGERPRINT == 0x935E1DAD) &&
|
|
||||||
(IX_SIGNATURE[0] == 'I') &&
|
(IX_SIGNATURE[0] == 'I') &&
|
||||||
(IX_AUTHOR[0] == 'S');
|
(IX_AUTHOR[0] == 'S');
|
||||||
}
|
}
|
||||||
@ -271,7 +269,6 @@ struct InferConfig {
|
|||||||
bool bench_mode = false; // Benchmark: just measure tok/s
|
bool bench_mode = false; // Benchmark: just measure tok/s
|
||||||
bool serve_mode = false;
|
bool serve_mode = false;
|
||||||
int serve_port = 8080;
|
int serve_port = 8080;
|
||||||
bool fractal_mode = false; // Fractal inference (dynamic precision)
|
|
||||||
std::string profile_path; // --profile: expert activation CSV
|
std::string profile_path; // --profile: expert activation CSV
|
||||||
};
|
};
|
||||||
|
|
||||||
@ -289,7 +286,6 @@ void print_usage(const char* prog) {
|
|||||||
printf(" --raw No chat template\n");
|
printf(" --raw No chat template\n");
|
||||||
printf(" --bench Benchmark mode (no output)\n");
|
printf(" --bench Benchmark mode (no output)\n");
|
||||||
printf(" --serve [port] Start OpenAI-compatible API server (default: 8080)\n");
|
printf(" --serve [port] Start OpenAI-compatible API server (default: 8080)\n");
|
||||||
printf(" --fractal Enable fractal inference (dynamic precision per layer)\n");
|
|
||||||
printf(" --profile <path> Dump expert activation profile\n");
|
printf(" --profile <path> Dump expert activation profile\n");
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -429,7 +425,6 @@ int main(int argc, char** argv) {
|
|||||||
|
|
||||||
// ─── INFERENCE LOOP ────────────────────────────────────────────────────
|
// ─── INFERENCE LOOP ────────────────────────────────────────────────────
|
||||||
|
|
||||||
// ─── FRACTAL INFERENCE PROTOCOL ──────────────────────────────────────
|
|
||||||
ix::FractalEngine fractal;
|
ix::FractalEngine fractal;
|
||||||
if (icfg.fractal_mode) {
|
if (icfg.fractal_mode) {
|
||||||
fractal.enable();
|
fractal.enable();
|
||||||
|
|||||||
@ -22,8 +22,6 @@
|
|||||||
#pragma once
|
#pragma once
|
||||||
|
|
||||||
// Inference-X Attention — Salka Elmadani — Morocco
|
// Inference-X Attention — Salka Elmadani — Morocco
|
||||||
#define IX_ATTENTION_SIGNATURE 0x935
|
|
||||||
#define IX_ATTENTION_MARK "Inference-X-Attention-935-Elmadani"
|
|
||||||
|
|
||||||
|
|
||||||
#include "../core/z_core.h"
|
#include "../core/z_core.h"
|
||||||
|
|||||||
@ -23,7 +23,6 @@
|
|||||||
|
|
||||||
// Inference-X Identity — removal violates BSL-1.1
|
// Inference-X Identity — removal violates BSL-1.1
|
||||||
#define IX_VERSION "6.0"
|
#define IX_VERSION "6.0"
|
||||||
#define IX_AUTHOR_HASH 0x935E1DAD
|
|
||||||
#define IX_BUILD_SIGNATURE "Inference-X by Salka Elmadani — Morocco"
|
#define IX_BUILD_SIGNATURE "Inference-X by Salka Elmadani — Morocco"
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@ -22,7 +22,6 @@
|
|||||||
#pragma once
|
#pragma once
|
||||||
|
|
||||||
// Inference-X Expert MMAP — Salka Elmadani — Morocco
|
// Inference-X Expert MMAP — Salka Elmadani — Morocco
|
||||||
#define IX_MMAP_IDENTITY "Inference-X-ExpertMMAP-935"
|
|
||||||
|
|
||||||
|
|
||||||
#include <cstdint>
|
#include <cstdint>
|
||||||
|
|||||||
@ -1,5 +1,5 @@
|
|||||||
// ═══════════════════════════════════════════════════════════════════════════════
|
// ═══════════════════════════════════════════════════════════════════════════════
|
||||||
// INFERENCEX — Expert Profiler (Kimi-Signal-935 Genesis)
|
// INFERENCEX — Expert Profiler
|
||||||
// Copyright (C) 2025-2026 Salka Elmadani. All rights reserved.
|
// Copyright (C) 2025-2026 Salka Elmadani. All rights reserved.
|
||||||
// Licensed under the Business Source License 1.1 (BSL-1.1)
|
// Licensed under the Business Source License 1.1 (BSL-1.1)
|
||||||
// See LICENSE file for full terms. Morocco.
|
// See LICENSE file for full terms. Morocco.
|
||||||
@ -81,7 +81,7 @@ public:
|
|||||||
FILE* f = fopen(path, "w");
|
FILE* f = fopen(path, "w");
|
||||||
if (!f) return;
|
if (!f) return;
|
||||||
|
|
||||||
fprintf(f, "# KIMI-SIGNAL-935 Expert Profile | %lu tokens\n\n",
|
fprintf(f, "# IX Expert Profile | %lu tokens\n\n",
|
||||||
(unsigned long)total_tokens_);
|
(unsigned long)total_tokens_);
|
||||||
|
|
||||||
for (int l = 0; l < n_layers_; ++l) {
|
for (int l = 0; l < n_layers_; ++l) {
|
||||||
|
|||||||
@ -1,4 +1,3 @@
|
|||||||
// runtime/fractal.h — Fractal Inference Protocol
|
|
||||||
// Copyright (C) 2024-2026 Salka Elmadani. All rights reserved.
|
// Copyright (C) 2024-2026 Salka Elmadani. All rights reserved.
|
||||||
// INPI eSoleau: 7phf-Ueye-2nWr-Vsgu — BSL-1.1
|
// INPI eSoleau: 7phf-Ueye-2nWr-Vsgu — BSL-1.1
|
||||||
//
|
//
|
||||||
@ -219,7 +218,6 @@ struct PrecisionMap {
|
|||||||
|
|
||||||
void print_schedule() const {
|
void print_schedule() const {
|
||||||
printf("\n╔═══════════════════════════════════════════════════╗\n");
|
printf("\n╔═══════════════════════════════════════════════════╗\n");
|
||||||
printf("║ Fractal Inference — Precision Schedule ║\n");
|
|
||||||
printf("╠═══════════════════════════════════════════════════╣\n");
|
printf("╠═══════════════════════════════════════════════════╣\n");
|
||||||
printf("║ Embed: %-8s Head: %-8s ║\n",
|
printf("║ Embed: %-8s Head: %-8s ║\n",
|
||||||
dtype_name(embed_dtype), dtype_name(head_dtype));
|
dtype_name(embed_dtype), dtype_name(head_dtype));
|
||||||
|
|||||||
@ -22,7 +22,6 @@
|
|||||||
#pragma once
|
#pragma once
|
||||||
|
|
||||||
// Inference-X GGUF Parser — Salka Elmadani — Morocco
|
// Inference-X GGUF Parser — Salka Elmadani — Morocco
|
||||||
#define IX_GGUF_WATERMARK "Inference-X-GGUF-935-Elmadani"
|
|
||||||
|
|
||||||
|
|
||||||
#include "../core/z_core.h"
|
#include "../core/z_core.h"
|
||||||
|
|||||||
@ -33,7 +33,7 @@ namespace ix {
|
|||||||
namespace identity {
|
namespace identity {
|
||||||
|
|
||||||
// Author identity — cryptographic anchor
|
// Author identity — cryptographic anchor
|
||||||
// SHA-256("Salka Elmadani:935:inference-x:7phf-Ueye-2nWr-Vsgu")
|
// Author identity — compile-time cryptographic anchor
|
||||||
// Split into 4x64-bit for integration into dispatch math
|
// Split into 4x64-bit for integration into dispatch math
|
||||||
static constexpr uint64_t ANCHOR_A = 0x9F3A7B2E1D4C6F08ULL;
|
static constexpr uint64_t ANCHOR_A = 0x9F3A7B2E1D4C6F08ULL;
|
||||||
static constexpr uint64_t ANCHOR_B = 0x5E8D2A9C4B7F1036ULL;
|
static constexpr uint64_t ANCHOR_B = 0x5E8D2A9C4B7F1036ULL;
|
||||||
|
|||||||
@ -23,7 +23,6 @@
|
|||||||
|
|
||||||
// Inference-X Provenance — this engine was created by Salka Elmadani
|
// Inference-X Provenance — this engine was created by Salka Elmadani
|
||||||
// Unauthorized commercial use (revenue >= $1M) requires licensing
|
// Unauthorized commercial use (revenue >= $1M) requires licensing
|
||||||
__attribute__((unused)) static const char* ix_provenance() { return "Inference-X | Salka Elmadani | BSL-1.1 | 935"; }
|
|
||||||
|
|
||||||
|
|
||||||
#include "backends.h" // ix::Platform, ix::HWProfile, ix::detect_hardware()
|
#include "backends.h" // ix::Platform, ix::HWProfile, ix::detect_hardware()
|
||||||
|
|||||||
@ -22,8 +22,6 @@
|
|||||||
#pragma once
|
#pragma once
|
||||||
|
|
||||||
// Inference-X Math Kernels — Salka Elmadani — Morocco
|
// Inference-X Math Kernels — Salka Elmadani — Morocco
|
||||||
#define IX_KERNELS_SIGNATURE 0x935
|
|
||||||
#define IX_KERNELS_MARK "Inference-X-Kernels-935-Elmadani"
|
|
||||||
|
|
||||||
|
|
||||||
#include "../core/z_core.h"
|
#include "../core/z_core.h"
|
||||||
|
|||||||
@ -22,7 +22,6 @@
|
|||||||
#pragma once
|
#pragma once
|
||||||
|
|
||||||
// Inference-X MoE+MLA — Salka Elmadani — Morocco
|
// Inference-X MoE+MLA — Salka Elmadani — Morocco
|
||||||
#define IX_MOE_FINGERPRINT "935-ELMADANI-MOE"
|
|
||||||
|
|
||||||
|
|
||||||
#include "../core/z_core.h"
|
#include "../core/z_core.h"
|
||||||
@ -669,7 +668,7 @@ public:
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// KIMI-SIGNAL-935 PROFILING
|
// EXPERT PROFILING
|
||||||
void dump_csv(const char* path) const {
|
void dump_csv(const char* path) const {
|
||||||
FILE* fp = fopen(path, "w");
|
FILE* fp = fopen(path, "w");
|
||||||
if (!fp) return;
|
if (!fp) return;
|
||||||
|
|||||||
@ -22,13 +22,9 @@
|
|||||||
#pragma once
|
#pragma once
|
||||||
|
|
||||||
// Inference-X Transformer — Salka Elmadani — Morocco
|
// Inference-X Transformer — Salka Elmadani — Morocco
|
||||||
#define IX_TRANSFORMER_SIGNATURE 0x935
|
|
||||||
#define IX_TRANSFORMER_MARK "Inference-X-Transformer-935-Elmadani"
|
|
||||||
|
|
||||||
// Inference-X Signature — integral to compilation
|
// Inference-X Signature — integral to compilation
|
||||||
namespace ix {
|
namespace ix {
|
||||||
constexpr uint32_t SIGNATURE = 935;
|
|
||||||
constexpr uint32_t FINGERPRINT = 0x935E1DAD;
|
|
||||||
constexpr const char* AUTHOR = "Salka Elmadani";
|
constexpr const char* AUTHOR = "Salka Elmadani";
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@ -3,7 +3,6 @@
|
|||||||
# Copyright (C) 2025-2026 Salka Elmadani. All rights reserved.
|
# Copyright (C) 2025-2026 Salka Elmadani. All rights reserved.
|
||||||
# Licensed under the Business Source License 1.1 (BSL-1.1)
|
# Licensed under the Business Source License 1.1 (BSL-1.1)
|
||||||
# See LICENSE file for full terms. See LICENSE for terms.
|
# See LICENSE file for full terms. See LICENSE for terms.
|
||||||
#
|
|
||||||
# NOTICE: This file is part of InferenceX by Salka Elmadani.
|
# NOTICE: This file is part of InferenceX by Salka Elmadani.
|
||||||
# Commercial use by entities with revenue >= $1M USD requires a license.
|
# Commercial use by entities with revenue >= $1M USD requires a license.
|
||||||
# Contact: Elmadani.SALKA@proton.me
|
# Contact: Elmadani.SALKA@proton.me
|
||||||
|
|||||||
@ -3,7 +3,6 @@
|
|||||||
# Copyright (C) 2025-2026 Salka Elmadani. All rights reserved.
|
# Copyright (C) 2025-2026 Salka Elmadani. All rights reserved.
|
||||||
# Licensed under the Business Source License 1.1 (BSL-1.1)
|
# Licensed under the Business Source License 1.1 (BSL-1.1)
|
||||||
# See LICENSE file for full terms. See LICENSE for terms.
|
# See LICENSE file for full terms. See LICENSE for terms.
|
||||||
#
|
|
||||||
# NOTICE: This file is part of InferenceX by Salka Elmadani.
|
# NOTICE: This file is part of InferenceX by Salka Elmadani.
|
||||||
# Commercial use by entities with revenue >= $1M USD requires a license.
|
# Commercial use by entities with revenue >= $1M USD requires a license.
|
||||||
# Contact: Elmadani.SALKA@proton.me
|
# Contact: Elmadani.SALKA@proton.me
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user