Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
C
docs/media: refreshed dashboard shots (full-residency 4 tok/s, disk 0), new Atlas galaxy, phone + sidebar shots
ZacharyZcR7bc9f6e2e985
diff --git a/README.md b/README.mdindex aec9c7e2..4045e9a2 100644--- a/README.md+++ b/README.md@@ -22,8 +22,9 @@ $ ./coli chat<p align="center"><img src="docs/media/colibri-dashboard.png" width="900" alt="colibrì web dashboard — live metrics, hardware panel, expert tiers"></p>-<p align="center"><em>The web dashboard (<code>./coli web</code>): a 744B model answering on 6× RTX 5090 —-live token metrics, the hardware panel, and the VRAM/RAM/disk expert tiers.</em></p>+<p align="center"><em>The web dashboard (<code>./coli web</code>): a 744B model at <strong>4 tok/s, TTFT 1.6 s, disk 0</strong> —+full expert residency on 6× RTX 5090, with live token metrics, the per-turn time breakdown,+the VRAM/RAM/disk tier bar and the live mini-brain in the corner.</em></p><p align="center"><img src="docs/media/colibri-brain.png" width="900" alt="the Brain page — 19,456 experts as a live cortex">@@ -32,6 +33,13 @@ live token metrics, the hardware panel, and the VRAM/RAM/disk expert tiers.</em>brightness is routing heat, and every expert routed in a turn flashes white. Hovering shows the expert's<a href="https://github.com/JustVugg/colibri/issues/175">measured topic affinity</a>.</em></p>+<p align="center">+ <img src="docs/media/colibri-atlas.png" width="900" alt="the Atlas page — the measured expert atlas as a 3-D galaxy">+</p>+<p align="center"><em>The <strong>Atlas</strong> page: the <a href="https://github.com/JustVugg/colibri/issues/175">measured expert atlas</a>+as a 3-D galaxy — 13,260 characterised experts, 1,041 replicated specialists clustering by topic+(poetry, law, Chinese, SQL…). Position is measured routing affinity, not a learned embedding. Drag to spin.</em></p>+## The ideaA 744B Mixture-of-Experts model activates only ~40B parameters per token — anddiff --git a/docs/api.md b/docs/api.mdindex c1f46d0e..d3b09f16 100644--- a/docs/api.md+++ b/docs/api.md@@ -98,3 +98,13 @@ The dashboard talks to the engine over a small line protocol and plain JSONendpoints — nothing heavier than the engine itself. `web/` is a pure OpenAI-APIclient (React + TypeScript) and also works against any other compatibleendpoint; the terminal `coli chat` remains the first-class interface.++The layout is responsive down to phone widths, and the sidebar carries the full+telemetry stack — hardware, scheduler, tier bar, per-turn time breakdown, tok/s+trend and per-GPU expert counts:++<p align="center">+ <img src="media/colibri-mobile.png" width="270" alt="the dashboard on a phone-sized viewport">+ + <img src="media/colibri-metrics.png" width="300" alt="the telemetry sidebar">+</p>diff --git a/docs/media/colibri-atlas.png b/docs/media/colibri-atlas.pngnew file mode 100644index 00000000..5e5e76eaBinary files /dev/null and b/docs/media/colibri-atlas.png differdiff --git a/docs/media/colibri-brain.png b/docs/media/colibri-brain.pngindex 0cd6c905..9ac5676a 100644Binary files a/docs/media/colibri-brain.png and b/docs/media/colibri-brain.png differdiff --git a/docs/media/colibri-dashboard.png b/docs/media/colibri-dashboard.pngindex 123fd3ee..d51aa087 100644Binary files a/docs/media/colibri-dashboard.png and b/docs/media/colibri-dashboard.png differdiff --git a/docs/media/colibri-metrics.png b/docs/media/colibri-metrics.pngnew file mode 100644index 00000000..853d6868Binary files /dev/null and b/docs/media/colibri-metrics.png differdiff --git a/docs/media/colibri-mobile.png b/docs/media/colibri-mobile.pngnew file mode 100644index 00000000..5c1c63c9Binary files /dev/null and b/docs/media/colibri-mobile.png differ