Initial commit: strata-docker Intel Arc runner for Strata

Thin wrapper over Strata's documented Docker route for the Intel Arc
(SYCL) engine: fetch a pinned upstream tag, build the strata-sycl-dev
image and the engine for bmg-g21, then run upstream setup for Gyro-M.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

1 files changed, 58 insertions, 0 deletions

diff --git a/AGENTS.md b/AGENTS.md
new file mode 100644
index 0000000..caddcd5
--- /dev/null
+++ b/AGENTS.md
@@ -0,0 +1,58 @@
+# AGENTS.md
+
+Guidance for AI coding agents working in this repository.
+
+## What this is
+
+`strata-docker`: a bash wrapper (`strata-docker`) that builds and runs the
+Intel Arc (SYCL) engine of [Strata](https://github.com/Niko1221/Strata) on a
+Slackware host, using upstream's own Docker route. Target: Arc B580 (12 GB,
+`xe` driver), model Gyro-M. Host needs only the `xe` driver, Docker and
+Python 3.10+ with venv. No oneAPI, Level Zero or compute runtime on the host:
+those live in the `strata-sycl-dev` image. Keep it a thin wrapper, do not
+reimplement anything upstream's scripts already do.
+
+## How upstream's Intel route works
+
+- There is no prebuilt Intel engine in Strata's releases. The engine is built
+  from source in the `strata-sycl-dev` image (`Strata/sycl/tools/Dockerfile`,
+  based on a community llama.cpp SYCL image, about 13 GB).
+- `setup.sh --backend sycl` runs `setup.py` in a `.venv` on the host, which
+  hands over to `sycl/setup_intel.py`. That writes the config and
+  `run-<model>.sh`. The server (`sycl/serve/server_intel.py`) runs on the
+  host. Only the engine runs in Docker, through `sycl/serve/strata-sycl.sh`.
+- `strata-sycl.sh` mounts the checkout's parent directory at `/work`. Hence
+  the layout: `Strata/` (checkout) and `Strata-data/` (models, about 92 GB for
+  Gyro-M) both inside this repo, gitignored. Symlinks pointing outside the
+  mount do not work in the container.
+- B580 is PCI id `e20b`, AOT target `bmg-g21`. `setup_intel.py` knows it.
+- Gyro is the one family whose experts are not streamed into VRAM: it needs
+  35 GB of RAM and VRAM together (Gyro-M). The host has about 30 GiB RAM and a
+  12 GB card, so close other programs before starting it.
+- Gyro on Arc was tested upstream only on an A750 (`i915`). The B580 is
+  untested natively; one WSL2 B580 report saw device loss.
+- On `xe`, asking for more VRAM than the card has does not fail: buffers
+  spill into RAM and the host can livelock. Never raise `--context` or lower
+  `--vram-reserve-mib` past what setup's fit rule picked.
+- Pictures are off by default on Battlemage (they reset a B70). Do not pass
+  `--vision yes`.
+- `docker build --pull` matters: a stale base can carry an ocloc that crashes
+  on Battlemage kernels (upstream #3219). `build.sh` checks for it.
+
+## Conventions
+
+- Pin the upstream tag in `ref` (`STRATA_REF` overrides). Bump it
+  deliberately, then rerun `image` (if `sycl/tools/Dockerfile` changed) and
+  `build`.
+- Placeholders only in code, docs, tests and commits.
+
+## Testing
+
+No test suite. Check by hand: `bash -n strata-docker`, then `./strata-docker
+build` must end with `BUILD EXIT 0` and `errors: 0`, and `./strata-docker
+setup --check` lists what fits.
+
+## Repo facts
+
+- License: GPLv2 only (`LICENSE`, header in each source file).
+- Work directly on master.