Source: tvm-ffi
Section: python
Priority: optional
Maintainer: Debian Deep Learning Team <debian-ai@lists.debian.org>
Uploaders: Mo Zhou <lumin@debian.org>
Build-Depends: debhelper-compat (= 13),
               dh-sequence-python3,
               cmake,
               python3-all,
               python3-all-dev,
               python3-setuptools,
               python3-scikit-build-core,
               cython3,
               python3-typing-extensions,
               python3-setuptools-scm,
               pybuild-plugin-pyproject,
               python3-pytest,
               python3-numpy,
               ninja-build,
               libdlpack-dev (>= 1.3~),
               libbacktrace-dev
Standards-Version: 4.6.2
Homepage: https://github.com/apache/tvm-ffi
Vcs-Git: https://salsa.debian.org/deeplearning-team/tvm-ffi.git
Vcs-Browser: https://salsa.debian.org/deeplearning-team/tvm-ffi

Package: python3-tvm-ffi
Architecture: any
Depends: ${python3:Depends}, ${shlibs:Depends}, ${misc:Depends},
         libdlpack-dev (>= 1.3~),
Description: Open ABI and FFI for Machine Learning Systems (python)
 Apache TVM FFI is an open ABI and FFI for machine learning systems. It is a
 minimal, framework-agnostic, yet flexible open convention with the following
 systems in mind:
 .
 * Kernel libraries - ship one wheel to support multiple frameworks, Python
   versions, and different languages.
 * Kernel DSLs - reusable open ABI for JIT and AOT kernel exposure frameworks
   and runtimes.
 * Frameworks and runtimes - a uniform extension point for ABI-compliant
   libraries and DSLs.
 * ML infrastructure - out-of-box bindings and interop across languages.
 * Coding agents - a unified mechanism for shipping generated code in
   production.
 .
 Apache TVM FFI Python package.

Package: libtvm-ffi-dev
Section: libdevel
Architecture: any
Depends: libtvm-ffi0 (= ${binary:Version}), ${misc:Depends},
         libdlpack-dev (>= 1.3~),
Description: Open ABI and FFI for Machine Learning Systems (Development files)
 Apache TVM FFI is an open ABI and FFI for machine learning systems. It is a
 minimal, framework-agnostic, yet flexible open convention with the following
 systems in mind:
 .
 * Kernel libraries - ship one wheel to support multiple frameworks, Python
   versions, and different languages.
 * Kernel DSLs - reusable open ABI for JIT and AOT kernel exposure frameworks
   and runtimes.
 * Frameworks and runtimes - a uniform extension point for ABI-compliant
   libraries and DSLs.
 * ML infrastructure - out-of-box bindings and interop across languages.
 * Coding agents - a unified mechanism for shipping generated code in
   production.
 .
 Apache TVM FFI development files.

Package: libtvm-ffi0
Section: libs
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}
Description: Open ABI and FFI for Machine Learning Systems (Shared library)
 Apache TVM FFI is an open ABI and FFI for machine learning systems. It is a
 minimal, framework-agnostic, yet flexible open convention with the following
 systems in mind:
 .
 * Kernel libraries - ship one wheel to support multiple frameworks, Python
   versions, and different languages.
 * Kernel DSLs - reusable open ABI for JIT and AOT kernel exposure frameworks
   and runtimes.
 * Frameworks and runtimes - a uniform extension point for ABI-compliant
   libraries and DSLs.
 * ML infrastructure - out-of-box bindings and interop across languages.
 * Coding agents - a unified mechanism for shipping generated code in
   production.
 .
 Apache TVM FFI shared objects.
