nbxtensor 0.0.2__tar.gz → 0.0.3__tar.gz

{nbxtensor-0.0.2 → nbxtensor-0.0.3}/CHANGELOG.md

@@ -7,6 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.0.3] - 2026-11-06
+
+### Fixed
+- **The backend is the one whose card is on the machine**: nbxtensor depends on the CUDA runtime wheel on Linux, and a runtime library loads without its card — on an AMD or Intel machine 0.0.2 named the CUDA backend and never tried HIP or Level Zero. Detection now tries only the runtime libraries of the GPU vendors present on the PCI bus (all of them where the bus cannot be read). The CUDA runtime wheel stays a Linux dependency: without an NVIDIA card it is not used.
+- **The package summary says where it runs**: wherever Triton runs — NVIDIA, AMD, Intel and Apple GPUs (it still named NVIDIA and Apple only).
+
 ## [0.0.2] - 2026-11-06
 
 ### Added
@@ -137,6 +143,7 @@ memory; the fix is in test).
 - **`flash_decode_split_kernel` and its route**: armed only by an environment switch (`NBX_FLASH_DECODE`, with `NBX_FD_BLOCK_N` and `NBX_FD_SEG`) and measured slower than the vector decode kernels; `flash_decode.py` keeps the fixed-order reduce they share.
 - **`conv1d_forward_kernel`**: launched by no route (a 1-D convolution runs through `conv2d`).
 
-[Unreleased]: https://github.com/NeuroBrix/nbxtensor/compare/v0.0.2...HEAD
+[Unreleased]: https://github.com/NeuroBrix/nbxtensor/compare/v0.0.3...HEAD
+[0.0.3]: https://github.com/NeuroBrix/nbxtensor/compare/v0.0.2...v0.0.3
 [0.0.2]: https://github.com/NeuroBrix/nbxtensor/compare/v0.0.1...v0.0.2
 [0.0.1]: https://github.com/NeuroBrix/nbxtensor/releases/tag/v0.0.1

{nbxtensor-0.0.2 → nbxtensor-0.0.3}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.5
 Name: nbxtensor
-Version: 0.0.2
-Summary: Run AI models without PyTorch: tensors, Triton kernels, planned memory and certified tuning, on NVIDIA and Apple GPUs.
+Version: 0.0.3
+Summary: Run AI models without PyTorch: tensors, Triton kernels, planned memory and certified tuning, wherever Triton runs — NVIDIA, AMD, Intel and Apple GPUs.
 Project-URL: Homepage, https://github.com/NeuroBrix/nbxtensor
 Project-URL: Source, https://github.com/NeuroBrix/nbxtensor
 Project-URL: Issues, https://github.com/NeuroBrix/nbxtensor/issues
@@ -492,7 +492,7 @@ with the tensor class (API.md §4).
 
 ## Versions
 
-The first publication was **0.0.1**; this is **0.0.2**. Each fix published after it increments the number (0.0.3,
+The first publication was **0.0.1**; this is **0.0.3**. Each fix published after it increments the number (0.0.4,
 …), with no alpha or beta label. The rewrite of the core in Rust will be **2.0.0**. `nbxtensor.__version__` is the
 installed version.
 

{nbxtensor-0.0.2 → nbxtensor-0.0.3}/README.md

@@ -472,7 +472,7 @@ with the tensor class (API.md §4).
 
 ## Versions
 
-The first publication was **0.0.1**; this is **0.0.2**. Each fix published after it increments the number (0.0.3,
+The first publication was **0.0.1**; this is **0.0.3**. Each fix published after it increments the number (0.0.4,
 …), with no alpha or beta label. The rewrite of the core in Rust will be **2.0.0**. `nbxtensor.__version__` is the
 installed version.
 

{nbxtensor-0.0.2 → nbxtensor-0.0.3}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "hatchling.build"
 
 [project]
 name = "nbxtensor"
-version = "0.0.2"
-description = "Run AI models without PyTorch: tensors, Triton kernels, planned memory and certified tuning, on NVIDIA and Apple GPUs."
+version = "0.0.3"
+description = "Run AI models without PyTorch: tensors, Triton kernels, planned memory and certified tuning, wherever Triton runs — NVIDIA, AMD, Intel and Apple GPUs."
 readme = "README.md"
 license = { text = "Apache-2.0" }
 requires-python = ">=3.10"

{nbxtensor-0.0.2 → nbxtensor-0.0.3}/src/nbxtensor/__init__.py

@@ -13,5 +13,5 @@ first publication is 0.0.1, each fix after it increments, the Rust rewrite is
 """
 
 #: the one version number; `pyproject.toml` states the same (tests/test_version.py)
-__version__ = "0.0.2"
+__version__ = "0.0.3"
 __all__: list = []

{nbxtensor-0.0.2 → nbxtensor-0.0.3}/src/nbxtensor/backend/runtime.py

@@ -141,6 +141,19 @@ _GPU_BACKENDS = {
 }
 
 
+#: the GPU vendor whose card each runtime-library backend drives (PCI vendor names, `backend.install_help`)
+_BACKEND_VENDOR = {"cuda": "nvidia", "hip": "amd"}
+
+
+def _on_this_machine(backends):
+    """The runtime-library backends whose vendor has a card on this machine's PCI bus, in table order — all of them
+    where the bus cannot be read (no sysfs). A runtime library loads without its card: the CUDA runtime wheel nbxtensor
+    depends on on Linux loaded on an AMD or Intel machine, named "cuda", and HIP / Level Zero were never tried."""
+    from nbxtensor.backend.install_help import pci_gpus
+    vendors = {v for v, _vid, _dev in pci_gpus()}
+    return [(n, b) for n, b in backends if not vendors or _BACKEND_VENDOR[n] in vendors]
+
+
 #: the backends found by asking for a DEVICE rather than by loading a runtime library, in order: (name, the probe's
 #: dotted path). Their runtime tables are not rows of `_GPU_BACKENDS` (another API than one C ABI): `_NATIVE_TABLES`.
 _DEVICE_PROBES = (("metal", "nbxtensor.backend.metal_device.metal_device_available"),
@@ -314,7 +327,7 @@ def gpu_backend() -> str:
         return _pin_triton_backend(forced)
     # The backend TABLE decides: the first vendor runtime the process can
     # load names the backend — adding a backend is adding a table entry.
-    for name, backend in _GPU_BACKENDS.items():
+    for name, backend in _on_this_machine(_GPU_BACKENDS.items()):
         for lib in backend["rt_libs"]:
             try:
                 ctypes.cdll.LoadLibrary(lib)

nbxtensor-0.0.3/tests/test_the_backend_is_the_card_on_the_machine.py

@@ -0,0 +1,19 @@
+"""The runtime-library backend is the one whose card is on the machine's PCI bus (`runtime._on_this_machine`).
+
+nbxtensor 0.0.2 depends on the CUDA runtime wheel on Linux, and a runtime library loads without its card: on an AMD or
+Intel machine `gpu_backend()` named "cuda" and HIP / Level Zero were never tried (the supervisor's reading of the 0.0.2
+metadata, 2026-11-06 18:25). What this test does if the code were wrong: "cuda" kept on a bus with only an AMD card, or
+a backend dropped where the bus cannot be read — red."""
+from nbxtensor.backend import install_help, runtime
+
+
+def test_only_the_backends_of_the_cards_present_are_tried(monkeypatch):
+    table = list(runtime._GPU_BACKENDS.items())
+    monkeypatch.setattr(install_help, "pci_gpus", lambda: [("amd", 0x1002, 0x744C)])
+    assert [n for n, _b in runtime._on_this_machine(table)] == ["hip"]
+    monkeypatch.setattr(install_help, "pci_gpus", lambda: [("intel", 0x8086, 0xE20B)])
+    assert runtime._on_this_machine(table) == []                     # Level Zero is probed for its device after
+    monkeypatch.setattr(install_help, "pci_gpus", lambda: [("nvidia", 0x10DE, 0x1DB1)])
+    assert [n for n, _b in runtime._on_this_machine(table)] == ["cuda"]
+    monkeypatch.setattr(install_help, "pci_gpus", lambda: [])      # no readable bus (macOS, a sandbox): as before
+    assert [n for n, _b in runtime._on_this_machine(table)] == ["cuda", "hip"]