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: state exactly which refusal checks ran (Linux packages) and the Windows PATH note for --version
Niko1221e88ee39d1d6b
diff --git a/docs/AMD_HIP.md b/docs/AMD_HIP.mdindex c9e85f580..cf9e27ba4 100644--- a/docs/AMD_HIP.md+++ b/docs/AMD_HIP.md@@ -89,8 +89,8 @@ What was run on real hardware:- **Checked on every package** (no RX 7000 or Strix Halo card involved): it builds and links; every library the binaries import is in thepackage or belongs to the OS (`packaging/binary_deps.py`); `package_engine.py --verify` passes; the GPU code inside each binary and- library lists exactly the architectures above (`llvm-objdump --offloading`); `strata --version` runs in a clean environment; on a- gfx1201 card the `rdna3`, `halo` and `rx7900` builds refuse to start with the plain message; the feed picks the right package for each+ library lists exactly the architectures above (`llvm-objdump --offloading`); `strata --version` runs in a clean environment (on Windows with the package's `rocm\bin` folder on PATH, which Control sets); on a+ gfx1201 card the Linux `halo` and `rx7900` builds refuse to start with the plain message (the Windows `rdna3` build was not run on an RX 9000 card: there is no Windows AMD machine); the feed picks the right package for eacharchitecture (`tests/terminal/test_release_matrix.py`).- **Not run by the maintainers:** any model on an RX 7000 card (gfx1100-1102) or a Strix Halo (gfx1151), on either OS. The maintainers haveno such card.diff --git a/docs/STRIX_HALO.md b/docs/STRIX_HALO.mdindex 473bf9677..651d9f9f6 100644--- a/docs/STRIX_HALO.md+++ b/docs/STRIX_HALO.md@@ -5,7 +5,7 @@ CPU and the GPU) through the same HIP backend as the Radeon cards in [AMD_HIP.mdEverything here was built and measured on one machine, the maintainers' Strix Halo box (Ryzen AI Max+ 395, 128 GB,Ubuntu 26.04, kernel 7.0, ROCm 7.14.1). Setup (`setup.sh`, `START-HERE.bat`) recognizes it from 0.1.40, by its PCI id (`1002:1586`, one id for the 8060S, 8050S and 8040S) and by`gfx1151` exactly: a Strix Point (890M / 880M, gfx1150), Krackan (860M / 840M, gfx1152) or Phoenix / Hawk Point (780M / 760M, gfx1103) Radeon is-named as what it is and not supported. On Linux setup compiles the engine for gfx1151 itself (the steps below are the same, by hand). The 0.2.0-beta release also has ready-made packages: `Strata-0.2.0-beta-linux-amd-strixhalo.AppImage` (engine `halo`, gfx1151, ROCm 7.14.1) and, on Windows, `Strata-0.2.0-beta-windows-hip-rdna3.exe` (engine `rdna3`: gfx1100, gfx1101, gfx1102 and gfx1151, ROCm 10.2.0a20260930); any app installer plus **Update engine** (or `strata update`) fetches the same package. What was run: both packages were built, linked and scanned, and they refuse to start on a card of another family; the maintainers have no Strix Halo and ran neither on one. The measurements on this page come from source builds on Linux (the maintainers' earlier box and community machines). Nobody has run a Strix Halo on Windows. The packaged engines do not carry the hipBLASLt table of section 3 yet (planned for 0.2.1), so their prompt reading is slower than the numbers below until then. A Windows zip of the 0.1.x START-HERE route without gfx1151 code is refused with a message, never used. Setup counts the GPU's memory as the BIOS carve-out plus the shared memory+named as what it is and not supported. On Linux setup compiles the engine for gfx1151 itself (the steps below are the same, by hand). The 0.2.0-beta release also has ready-made packages: `Strata-0.2.0-beta-linux-amd-strixhalo.AppImage` (engine `halo`, gfx1151, ROCm 7.14.1) and, on Windows, `Strata-0.2.0-beta-windows-hip-rdna3.exe` (engine `rdna3`: gfx1100, gfx1101, gfx1102 and gfx1151, ROCm 10.2.0a20260930); any app installer plus **Update engine** (or `strata update`) fetches the same package. What was run: both packages were built, linked and scanned, and the Linux package refuses to start on a card of another family (tried on an RX 9000 card); the maintainers have no Strix Halo and ran neither on one. The measurements on this page come from source builds on Linux (the maintainers' earlier box and community machines). Nobody has run a Strix Halo on Windows. The packaged engines do not carry the hipBLASLt table of section 3 yet (planned for 0.2.1), so their prompt reading is slower than the numbers below until then. A Windows zip of the 0.1.x START-HERE route without gfx1151 code is refused with a message, never used. Setup counts the GPU's memory as the BIOS carve-out plus the shared memory(the GTT pool; on Windows half the RAM) and recommends UD-IQ4_XS from about 80 GB of memory; it changes no BIOS or kernel setting.What the engine does differently on this chip:diff --git a/docs/release-notes-0.2.0.md b/docs/release-notes-0.2.0.mdindex 8b91d2e12..4959161f3 100644--- a/docs/release-notes-0.2.0.md+++ b/docs/release-notes-0.2.0.md@@ -83,7 +83,7 @@ Every speed number below is a median of interleaved pairs against the previous d- **Mac:** no picture reader yet; macOS 15 or newer. The app and the Terminal are signed and notarised by Apple.- **Windows:** the installers are not code-signed yet, so Windows shows "Windows protected your PC": choose **More info**, then **Run anyway**.- **Windows with an AMD card:** the installer and the GPU picture reader are built, but nothing has run on a real AMD card on Windows. The gfx12 prompt defaults are opt-in there.-- **AMD RX 7000 (gfx1100-1102) and Strix Halo (gfx1151):** the packages are built, linked and scanned (library imports, file hashes, the GPU code inside each binary, `--version` in a clean environment, a clean refusal on an RX 9000 card, update-feed selection tests). The maintainers have not run them on an RX 7000 or a Strix Halo card. What other people ran: an RX 7900 XTX on Windows 11 ran the earlier ready-made Windows engine (0.1.40, report #1173), and Strix Halo owners ran Linux builds made from source on the ROCm 7.14 line (`bench/results/COMMUNITY.md`). Nobody has run Strix Halo on Windows. The packaged AMD engines do not carry the hipBLASLt tuning tables yet (planned for 0.2.1), so prompt reading is slower than the source-build numbers in [STRIX_HALO.md](STRIX_HALO.md) and [AMD_HIP.md](AMD_HIP.md).+- **AMD RX 7000 (gfx1100-1102) and Strix Halo (gfx1151):** the packages are built, linked and scanned (library imports, file hashes, the GPU code inside each binary, `--version` in a clean environment, a clean refusal of the Linux packages on an RX 9000 card, update-feed selection tests). The maintainers have not run them on an RX 7000 or a Strix Halo card. What other people ran: an RX 7900 XTX on Windows 11 ran the earlier ready-made Windows engine (0.1.40, report #1173), and Strix Halo owners ran Linux builds made from source on the ROCm 7.14 line (`bench/results/COMMUNITY.md`). Nobody has run Strix Halo on Windows. The packaged AMD engines do not carry the hipBLASLt tuning tables yet (planned for 0.2.1), so prompt reading is slower than the source-build numbers in [STRIX_HALO.md](STRIX_HALO.md) and [AMD_HIP.md](AMD_HIP.md).- **Mini PCs with a Radeon 780M / 880M / 890M:** the matrix-core prompt defaults are parked. On the 780M the GPU reset (MES REMOVE_QUEUE) when they were tried; the iGPU keeps its opt-in switches.- **R9700:** about half of the fresh engines with MTP read prompts 10-23% slower than the others (4K: about 1,350 instead of 1,700 tok/s). Not seen on NVIDIA; the cause is not found.- **Docker images are not published yet;** build them yourself (`docs/DOCKER.md`).