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++

Intel Arc pictures stay opt-in until the SYCL engine's first-picture GPU fault is fixed; UPDATES: publish as a normal release

Niko122176e4fef39843
diff --git a/docs/INTEL.md b/docs/INTEL.md
index 8d42e9f9f..915d2379c 100644
--- a/docs/INTEL.md
+++ b/docs/INTEL.md
@@ -772,11 +772,14 @@ is 0.012), first-token KL 0.0017 (floor 0.0005), top-1 agreement 99.7%. HumanEva
## Not done
-- Images on the llama.cpp config: not wired. On the SYCL port pictures are on by default (0.2.0): `setup --backend sycl` compiles the
- portable CPU reader `strata-vision` (the program the AMD packages carry beside their engine) into `engine-sycl/`, the server runs
- it on the host, and the engine in the container reads its embeddings from the host's `/dev/shm`, which `strata-sycl.sh` shares
- (`STRATA_SYCL_SHM=0` keeps a private one). `--vision no` turns pictures off. A SYCL GPU reader does not exist yet, so every Arc
- reads pictures on the CPU (a few seconds each), whatever its memory; that is later work.
+- Images on the llama.cpp config: not wired. On the SYCL port pictures are wired but opt-in (`setup --backend sycl --vision yes`):
+ setup compiles the portable CPU reader `strata-vision` (the program the AMD packages carry beside their engine) into `engine-sycl/`,
+ the server runs it on the host, and the engine in the container reads its embeddings from the host's `/dev/shm`, which
+ `strata-sycl.sh` shares (`STRATA_SYCL_SHM=0` keeps a private one). A SYCL GPU reader does not exist yet, so every Arc reads
+ pictures on the CPU (a few seconds each). They are not on by default because the first picture request on the Arc Pro B70
+ (engine 0.1.45, IQ3_S, 2026-10-19) hung the GPU: the xe driver logged an engine reset and `Fault response: Unsuccessful -EINVAL`
+ and the request ended 503. Text was not affected by this wiring (the reader and the shared `/dev/shm` are only used for pictures);
+ the engine's vision path on SYCL needs a look first (`setup_intel.PICTURES_ON_BY_DEFAULT` flips the default).
- Speculative decoding on the llama.cpp path (the GGUF carries no draft layer llama.cpp can use). The SYCL
port has it (MTP draft layer, `--mtp`).
diff --git a/packaging/UPDATES.md b/packaging/UPDATES.md
index 7e6d8d701..14df304bd 100644
--- a/packaging/UPDATES.md
+++ b/packaging/UPDATES.md
@@ -128,6 +128,8 @@ as an asset: `strata-feed.json`, `strata-feed.json.sig`, `install-manifest.txt`,
app installer with `latest.json` (the Tauri updater endpoint). `STRATA_FEED` (installers) and `--feed` / `STRATA_UPDATE_FEED` (`strata update`) override the
address. Nothing in this tree uploads anything.
+Publish as a normal release (latest): a pre-release is not found by `latest/download`, so the installers, `strata update` and the app updater would get a 404. The `latest` release must carry every file listed above, so a later hotfix release repeats them all.
+
## Testing locally
Everything above runs against a folder or a loopback server: `tests/terminal/test_update_feed.py` (signatures, hashes, downgrades, selection),
diff --git a/sycl/setup_intel.py b/sycl/setup_intel.py
index fca5dc8d6..3e327d377 100644
--- a/sycl/setup_intel.py
+++ b/sycl/setup_intel.py
@@ -11,7 +11,7 @@ setup.py's, unchanged. What is replaced:
sized from sysfs;
- the engine step: the SYCL build (build-sycl-aot/strata, run in the strata-sycl-dev image by
sycl/serve/strata-sycl.sh; docs/INTEL.md) instead of a CUDA/HIP build;
- - pictures: on by default, read by the portable CPU reader (`strata-vision`, the program the AMD packages carry beside
+ - pictures (opt-in for now, see PICTURES_ON_BY_DEFAULT): read by the portable CPU reader (`strata-vision`, the program the AMD packages carry beside
their engine, compiled here by setup's own step) on the host; it hands the image embeddings to the engine through
/dev/shm, which strata-sycl.sh shares with the container. A SYCL GPU reader does not exist yet, so "gpu" is read as "cpu"
here; --vision no is the off switch;
@@ -122,6 +122,12 @@ def drop(args, name, value=False):
del args[i:i + 1 + int(value)]
+# Pictures on an Intel Arc work end to end up to the engine (the CPU reader encodes, the embeddings reach the container through /dev/shm)
+# but the first picture request on the Arc Pro B70 (engine 0.1.45 SYCL, IQ3_S, 2026-10-19) hung the GPU: the xe driver logged an engine
+# reset (ccs + bcs) and "Fault response: Unsuccessful -EINVAL", and the request ended 503. Until the SYCL engine's vision path is fixed
+# pictures stay opt-in here (--vision yes); flip this to True to make them the default like on the other makes of card.
+PICTURES_ON_BY_DEFAULT = False
+
READER_DIR = ROOT / "engine-sycl" # the folder setup treats as the engine's: BUILD.json and, for pictures, the CPU reader strata-vision
@@ -397,6 +403,8 @@ def install(argv) -> None:
sys.argv = [str(ROOT / "setup.py"), *argv]
if "--backend" not in argv:
sys.argv += ["--backend", "hip"]
+ if "--vision" not in argv and not PICTURES_ON_BY_DEFAULT:
+ sys.argv += ["--vision", "none"]
if "--low-ram" not in argv:
sys.argv += ["--low-ram", "off"]
sys.exit(S.main())
diff --git a/tools/test_setup_sycl.py b/tools/test_setup_sycl.py
index 2f3ad0759..25d1bca59 100644
--- a/tools/test_setup_sycl.py
+++ b/tools/test_setup_sycl.py
@@ -223,8 +223,8 @@ class ToSycl(unittest.TestCase):
self.assertTrue(m.small_card(10.0, "xe"))
self.assertFalse(m.small_card(32.0, "xe"))
- def test_pictures_are_on_by_default_read_on_the_cpu_and_the_vision_section_survives(self):
- """Intel Arc: the CPU reader (strata-vision) on the host, --vision no is the off switch; "gpu" is read as "cpu" (no SYCL GPU reader)."""
+ def test_pictures_asked_for_are_read_on_the_cpu_and_the_vision_section_survives(self):
+ """Intel Arc: the CPU reader (strata-vision) on the host when asked for (--vision yes); "gpu" is read as "cpu" (no SYCL GPU reader)."""
m = self.mod()
for asked in (None, "yes", "gpu", "cpu", "on"):
self.assertEqual(m.intel_vision(asked, 8.0), "cpu")
@@ -239,9 +239,12 @@ class ToSycl(unittest.TestCase):
self.assertEqual(c["vision"], section) # host paths: the reader runs on the host, not in the container
self.assertIn("--vision", c["args"])
- def test_setup_intel_no_longer_forces_pictures_off(self):
+ def test_pictures_are_opt_in_on_the_arc_until_the_engine_fault_is_fixed(self):
+ """The first picture on the Arc Pro B70 hung the GPU (xe engine reset, 2026-10-19): off unless asked, --vision yes turns it on."""
+ m = self.mod()
+ self.assertFalse(m.PICTURES_ON_BY_DEFAULT)
src = (ROOT / "sycl" / "setup_intel.py").read_text(encoding="utf-8")
- self.assertNotIn('sys.argv += ["--vision", "none"]', src)
+ self.assertIn('if "--vision" not in argv and not PICTURES_ON_BY_DEFAULT:', src)
self.assertIn("S.hip_vision = intel_vision", src)
self.assertIn("S.build_vision_cpu(", src) # the CPU reader is compiled by setup's own step