tensoracle 1.0.0__tar.gz → 1.0.1__tar.gz

{tensoracle-1.0.0 → tensoracle-1.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: tensoracle
-Version: 1.0.0
+Version: 1.0.1
 Summary: Build, save, reuse, and execute TensorRT engines from safetensors weights
 Project-URL: documentation, https://sync-dev-org.github.io/tensoracle/
 Project-URL: repository, https://github.com/sync-dev-org/tensoracle
@@ -8,7 +8,7 @@ Project-URL: issues, https://github.com/sync-dev-org/tensoracle/issues
 Author-email: minamik <mia@sync.dev>
 License-Expression: MIT
 License-File: LICENSE
-Classifier: Development Status :: 4 - Beta
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: GPU :: NVIDIA CUDA :: 13
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
@@ -142,7 +142,7 @@ handle = open_engine(
 engine = handle.engine  # Keep handle.runtime alive while using the engine.
 ```
 
-Saved files live in the `tensoracle` directory under `XDG_CACHE_HOME`, or under the home directory's `.cache` when that variable is unset. The same rule applies on every OS; on Windows the home directory is `%USERPROFILE%`, so the default is `%USERPROFILE%\.cache\tensoracle`. The cache identity includes the contents of all declared safetensors weight files and optional `plugins` files, the engine name, graph version, input shapes, builder settings, GPU product name, OS, CPU architecture, and TensorRT version. Raise `graph_version` when graph code changes; without a version change, the previous engine is reused. Use a different `name` or `graph_version` for engines with different tensor types, such as fp32 and fp16. Include in `graph_version` any other caller value that changes the engine contents but is not part of the cache identity, such as a plugin manifest or a build recipe. Pass `force_rebuild=True` to replace a cached engine even when it is intact. tensoracle closes a saved engine file after reading it, so another process using an opened engine does not block replacement. On Windows, a process that keeps the saved file itself open prevents replacement or removal with `PermissionError`; after that process closes the file, a file left empty by the failed rebuild is rejected as `CorruptEngineError` and can be rebuilt with `force_rebuild=True`.
+Saved files live in the `tensoracle` directory under `XDG_CACHE_HOME`, or under the home directory's `.cache` when that variable is unset. The same rule applies on every OS; on Windows the home directory is `%USERPROFILE%`, so the default is `%USERPROFILE%\.cache\tensoracle`. The cache identity includes the contents of all declared safetensors weight files and optional `plugins` files, the engine name, graph version, input shapes, builder settings, the GPU's compatibility properties, OS, CPU architecture, and TensorRT version. The GPU is the device of the current CUDA context, or device 0 when no context is current. Its properties are the product name, compute capability, memory bus width, L2 cache size, shared memory limits, texture alignment, multiprocessor count, whether the GPU is integrated, ECC mode, and total memory; another device with the same properties reuses the saved engine. Raise `graph_version` when graph code changes; without a version change, the previous engine is reused. Use a different `name` or `graph_version` for engines with different tensor types, such as fp32 and fp16. Include in `graph_version` any other caller value that changes the engine contents but is not part of the cache identity, such as a plugin manifest or a build recipe. Pass `force_rebuild=True` to replace a cached engine even when it is intact. tensoracle closes a saved engine file after reading it, so another process using an opened engine does not block replacement. On Windows, a process that keeps the saved file itself open prevents replacement or removal with `PermissionError`; after that process closes the file, a file left empty by the failed rebuild is rejected as `CorruptEngineError` and can be rebuilt with `force_rebuild=True`.
 
 `plugins` names native TensorRT plugin libraries. Both `open_engine` and `build_serialized_engine` accept it. Each function checks that every library exports `getCreators`, loads it through TensorRT's registry, and retains it for the process before building the graph or deserializing an engine. Repeating the same library does not register it twice. `open_engine` also hashes the loaded library bytes into the engine identity; a changed library selects a different saved engine in a new process. A missing, unreadable, or incompatible library, or a library changed after loading in the same process, raises `PluginLibraryError` before a cached plan is opened. Keep the library and its cubin bundle together in the caller's wheel.
 
@@ -302,7 +302,7 @@ Use `PluginBase(name, plugin_namespace, std::move(fields), residual_io())` in th
 
 For configurations the declaration cannot express, such as multiple outputs or computed output shapes, developers can override the virtual V3 methods in a derived class or ask tensoracle's maintainers to extend the declaration.
 
-`tensoracle.bundle.inspect_bundle(bundle_directory, plugin=library_path)` checks the manifest, each cubin's SHA-256 and actual ELF SM, the supported hidden arguments and zero scratch sizes, and the cubin bytes embedded in the library. `inspect_wheel(wheel_path, plugin="path/inside/wheel.so")` performs the same checks on a wheel without installing it. Their distinct exceptions identify a missing cubin, corrupt cubin, false SM claim, or plugin and bundle mismatch. The manifest records Triton, ptxas, and kernel source digests without a producer host or OS path. The TensorRT versions tested with the included example are listed below.
+`tensoracle.bundle.inspect_bundle(bundle_directory, plugin=library_path)` checks the manifest, each cubin's SHA-256 and actual ELF SM, the supported hidden arguments and zero scratch sizes, and the cubin bytes embedded in the library. `inspect_wheel(wheel_path, plugin="path/inside/wheel.so")` performs the same checks on a wheel without installing it. Their distinct exceptions identify a missing cubin, corrupt cubin, false SM claim, or plugin and bundle mismatch. The manifest records the Triton and ptxas versions and each kernel's source SHA-256, without a producer host or OS path. The TensorRT versions tested with the included example are listed below.
 
 ## Tested environments
 

{tensoracle-1.0.0 → tensoracle-1.0.1}/README.md

@@ -111,7 +111,7 @@ handle = open_engine(
 engine = handle.engine  # Keep handle.runtime alive while using the engine.
 ```
 
-Saved files live in the `tensoracle` directory under `XDG_CACHE_HOME`, or under the home directory's `.cache` when that variable is unset. The same rule applies on every OS; on Windows the home directory is `%USERPROFILE%`, so the default is `%USERPROFILE%\.cache\tensoracle`. The cache identity includes the contents of all declared safetensors weight files and optional `plugins` files, the engine name, graph version, input shapes, builder settings, GPU product name, OS, CPU architecture, and TensorRT version. Raise `graph_version` when graph code changes; without a version change, the previous engine is reused. Use a different `name` or `graph_version` for engines with different tensor types, such as fp32 and fp16. Include in `graph_version` any other caller value that changes the engine contents but is not part of the cache identity, such as a plugin manifest or a build recipe. Pass `force_rebuild=True` to replace a cached engine even when it is intact. tensoracle closes a saved engine file after reading it, so another process using an opened engine does not block replacement. On Windows, a process that keeps the saved file itself open prevents replacement or removal with `PermissionError`; after that process closes the file, a file left empty by the failed rebuild is rejected as `CorruptEngineError` and can be rebuilt with `force_rebuild=True`.
+Saved files live in the `tensoracle` directory under `XDG_CACHE_HOME`, or under the home directory's `.cache` when that variable is unset. The same rule applies on every OS; on Windows the home directory is `%USERPROFILE%`, so the default is `%USERPROFILE%\.cache\tensoracle`. The cache identity includes the contents of all declared safetensors weight files and optional `plugins` files, the engine name, graph version, input shapes, builder settings, the GPU's compatibility properties, OS, CPU architecture, and TensorRT version. The GPU is the device of the current CUDA context, or device 0 when no context is current. Its properties are the product name, compute capability, memory bus width, L2 cache size, shared memory limits, texture alignment, multiprocessor count, whether the GPU is integrated, ECC mode, and total memory; another device with the same properties reuses the saved engine. Raise `graph_version` when graph code changes; without a version change, the previous engine is reused. Use a different `name` or `graph_version` for engines with different tensor types, such as fp32 and fp16. Include in `graph_version` any other caller value that changes the engine contents but is not part of the cache identity, such as a plugin manifest or a build recipe. Pass `force_rebuild=True` to replace a cached engine even when it is intact. tensoracle closes a saved engine file after reading it, so another process using an opened engine does not block replacement. On Windows, a process that keeps the saved file itself open prevents replacement or removal with `PermissionError`; after that process closes the file, a file left empty by the failed rebuild is rejected as `CorruptEngineError` and can be rebuilt with `force_rebuild=True`.
 
 `plugins` names native TensorRT plugin libraries. Both `open_engine` and `build_serialized_engine` accept it. Each function checks that every library exports `getCreators`, loads it through TensorRT's registry, and retains it for the process before building the graph or deserializing an engine. Repeating the same library does not register it twice. `open_engine` also hashes the loaded library bytes into the engine identity; a changed library selects a different saved engine in a new process. A missing, unreadable, or incompatible library, or a library changed after loading in the same process, raises `PluginLibraryError` before a cached plan is opened. Keep the library and its cubin bundle together in the caller's wheel.
 
@@ -271,7 +271,7 @@ Use `PluginBase(name, plugin_namespace, std::move(fields), residual_io())` in th
 
 For configurations the declaration cannot express, such as multiple outputs or computed output shapes, developers can override the virtual V3 methods in a derived class or ask tensoracle's maintainers to extend the declaration.
 
-`tensoracle.bundle.inspect_bundle(bundle_directory, plugin=library_path)` checks the manifest, each cubin's SHA-256 and actual ELF SM, the supported hidden arguments and zero scratch sizes, and the cubin bytes embedded in the library. `inspect_wheel(wheel_path, plugin="path/inside/wheel.so")` performs the same checks on a wheel without installing it. Their distinct exceptions identify a missing cubin, corrupt cubin, false SM claim, or plugin and bundle mismatch. The manifest records Triton, ptxas, and kernel source digests without a producer host or OS path. The TensorRT versions tested with the included example are listed below.
+`tensoracle.bundle.inspect_bundle(bundle_directory, plugin=library_path)` checks the manifest, each cubin's SHA-256 and actual ELF SM, the supported hidden arguments and zero scratch sizes, and the cubin bytes embedded in the library. `inspect_wheel(wheel_path, plugin="path/inside/wheel.so")` performs the same checks on a wheel without installing it. Their distinct exceptions identify a missing cubin, corrupt cubin, false SM claim, or plugin and bundle mismatch. The manifest records the Triton and ptxas versions and each kernel's source SHA-256, without a producer host or OS path. The TensorRT versions tested with the included example are listed below.
 
 ## Tested environments
 

{tensoracle-1.0.0 → tensoracle-1.0.1}/docs/api/index.md

@@ -12,6 +12,8 @@ The following names are available directly from `tensoracle`.
 
 ::: tensoracle._build.build_serialized_engine
 
+::: tensoracle._build.ShapeTensorOutputWarning
+
 ## Saved engines
 
 ::: tensoracle._cache.TensorSpec

{tensoracle-1.0.0 → tensoracle-1.0.1}/docs/optimization.md

@@ -20,7 +20,7 @@ First check whether a combination of standard TensorRT layers can preserve the o
 
 - **tensoracle tools:** `tensoracle.producer.compile_bundle` generates cubins and a manifest for supported GPU generations. The shared C++ plugin helpers support a caller-built native plugin with declared tensor types, formats, and an input whose shape the output copies; `tensoracle.bundle.inspect_bundle` or `inspect_wheel` checks the cubins and their match with the plugin. Pass the plugin library through `plugins=` to `build_serialized_engine` or `open_engine`. Follow [Build a cubin plugin](index.md#build-a-cubin-plugin) for the `PluginIO` declaration, including fp16 / HWC8 and two-input examples, and the [cubin plugin example](https://github.com/sync-dev-org/tensoracle/blob/main/examples/cubin_plugin/README.md) for the generation, build, and inspection operations.
 - **You provide:** Identify the bottleneck, write the kernel and model-specific plugin behavior, choose its supported shapes and types, build and package its native library, and run the resulting engines. An fp32 kernel must not use TF32.
-- **Gate:** For a custom cubin plugin, the bundle and plugin inspections must pass. Reapply stage 1 to the replacement's fp32 engine against the same fixed PyTorch reference. If using fp16, reapply stage 2 against an accepted fp32 engine with the same limits and model-specific measurements. Advance only when the replacement meets those quality gates; otherwise retain the accepted implementation.
+- **Gate:** For a custom cubin plugin, the bundle and plugin inspections must pass. Reapply stage 1 to the replacement's fp32 engine against the same fixed PyTorch reference. If using a lower precision engine, reapply stage 2 against an accepted fp32 engine with the same limits and model-specific measurements. Advance only when the replacement meets those quality gates; otherwise retain the accepted implementation.
 
 ## 4. Measure speed under isolated load
 

{tensoracle-1.0.0 → tensoracle-1.0.1}/examples/cubin_plugin/README.md

@@ -30,7 +30,7 @@ Follow [Prepare a TensorRT SDK](../../docs/tensorrt-sdk.md) to obtain and verify
 CMAKE_ARGS="-DTENSORRT_ROOT=$TENSORRT_ROOT" uv build examples/cubin_plugin --wheel
 ```
 
-The example's build backend and CUDA tooling belong to this project, not to tensoracle's runtime dependencies. Before installation, inspect the wheel with `tensoracle.bundle.inspect_wheel(wheel, plugin="example_cubin_plugin/libtensoracle_example_plugin.so")`. This compares the library's embedded digest and cubin bytes with the manifest and cubin files.
+The example's build backend and CUDA tooling belong to this project, not to tensoracle's runtime dependencies. Before installation, inspect the wheel with `tensoracle.bundle.inspect_wheel(wheel, plugin="example_cubin_plugin/libtensoracle_example_plugin.so")`. For a wheel built on Windows, pass `plugin="example_cubin_plugin/tensoracle_example_plugin.dll"`. This compares the library's embedded digest and cubin bytes with the manifest and cubin files.
 
 Install the tensoracle wheel and this example wheel into a runtime Python environment with TensorRT 11 and `cuda-python`, but without Triton, torch, or the TensorRT SDK. `open_engine` registers the library before calling `graph` or opening a saved engine. The tests use two separate processes and an `XDG_CACHE_HOME` directory to verify that the second process reuses the saved engine without building a graph.
 

{tensoracle-1.0.0 → tensoracle-1.0.1}/pyproject.toml

@@ -7,7 +7,7 @@ readme = "README.md"
 license = "MIT"
 license-files = ["LICENSE"]
 classifiers = [
-    "Development Status :: 4 - Beta",
+    "Development Status :: 5 - Production/Stable",
     "Environment :: GPU :: NVIDIA CUDA :: 13",
     "Intended Audience :: Developers",
     "License :: OSI Approved :: MIT License",

{tensoracle-1.0.0 → tensoracle-1.0.1}/src/tensoracle/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '1.0.0'
-__version_tuple__ = version_tuple = (1, 0, 0)
+__version__ = version = '1.0.1'
+__version_tuple__ = version_tuple = (1, 0, 1)
 
 __commit_id__ = commit_id = None

{tensoracle-1.0.0 → tensoracle-1.0.1}/tests/test_distribution.py

@@ -410,7 +410,7 @@ def test_wheel_metadata_describes_the_public_package(distributions):
     assert metadata.get_all("License-File") == ["LICENSE"]
     assert metadata["Requires-Python"] == "<3.14,>=3.12"
     assert set(metadata.get_all("Classifier", [])) == {
-        "Development Status :: 4 - Beta",
+        "Development Status :: 5 - Production/Stable",
         "Environment :: GPU :: NVIDIA CUDA :: 13",
         "Intended Audience :: Developers",
         "License :: OSI Approved :: MIT License",