Skip to content

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

C++

docs/GYRO.md: clone the rc2 branch (Strata v0.1.40.3 + Gyro)

Laurent26da97bde092
diff --git a/docs/GYRO.md b/docs/GYRO.md
index 99f6a6f58..a12c2005e 100644
--- a/docs/GYRO.md
+++ b/docs/GYRO.md
@@ -19,7 +19,13 @@ Qwen3.8-Flash-Next models. It is not the GGUF draft file from the Gyro repositor
## Quick setup
-From a Strata checkout:
+Gyro support lives on the `rc2` branch of the agentionai Strata fork: Strata v0.1.40.3 plus the trellis types
+(TQ2_T / TQK6 / TQK7), the Hadamard rotation and the CPU trellis kernels.
+
+```sh
+git clone -b rc2 https://github.com/agentionai/Strata
+cd Strata
+```
`tools/gyro_setup.sh` does every step below on Linux:
@@ -34,7 +40,7 @@ It prints the command that starts the server. The steps, by hand:
## 1. Build
-Strata's GGML dependency must be the agentionai llama.cpp fork, which has the trellis types:
+From the `rc2` checkout above. Strata's GGML dependency must be the agentionai llama.cpp fork, which has the trellis types:
```sh
git clone --depth 1 https://github.com/agentionai/llama.cpp ../agention-llama.cpp