NVIDIA · Andy-Jost · Jul 8, 2026 · Jul 8, 2026 · Jul 8, 2026 · Jul 8, 2026
diff --git a/cuda_core/docs/source/api.rst b/cuda_core/docs/source/api.rst
@@ -78,6 +78,45 @@ Memory management
    VirtualMemoryResourceOptions
 
 
+CUDA compilation toolchain
+--------------------------
+
+.. currentmodule:: cuda.core
+
+.. autosummary::
+   :toctree: generated/
+
+   :template: autosummary/cyclass.rst
+
+   Program
+   Linker
+   ObjectCode
+   Kernel
+
+   :template: dataclass.rst
+
+   ProgramOptions
+   LinkerOptions
+
+Program caches
+``````````````
+
+``Program.compile`` accepts a ``cache=`` keyword argument that integrates
+with any :class:`~cuda.core.utils.ProgramCacheResource`, so callers can
+avoid recompiling identical source + options + target without writing the
+:func:`~cuda.core.utils.make_program_cache_key` lookup by hand.
+
+.. currentmodule:: cuda.core.utils
+
+.. autosummary::
+   :toctree: generated/
+
+   ProgramCacheResource
+   InMemoryProgramCache
+   FileStreamProgramCache
+   make_program_cache_key
+
+
 CUDA graphs
 -----------
 
@@ -89,6 +128,8 @@ CPU overhead. Graphs can be constructed in two ways:
 edges. Both produce an executable :class:`~graph.Graph` that can be
 launched on a :class:`Stream`.
 
+.. currentmodule:: cuda.core
+
 .. autosummary::
    :toctree: generated/
 
@@ -138,6 +179,8 @@ Each subclass exposes attributes unique to its operation type.
 Graphics interoperability
 -------------------------
 
+.. currentmodule:: cuda.core
+
 .. autosummary::
    :toctree: generated/
 
@@ -149,6 +192,8 @@ Graphics interoperability
 Tensor Memory Accelerator (TMA)
 -------------------------------
 
+.. currentmodule:: cuda.core
+
 .. autosummary::
    :toctree: generated/
 
@@ -208,47 +253,6 @@ The associated enumerations —
 alongside the other ``cuda.core`` enumerations.
 
 
-CUDA compilation toolchain
---------------------------
-
-.. currentmodule:: cuda.core
-
-.. autosummary::
-   :toctree: generated/
-
-   :template: autosummary/cyclass.rst
-
-   Program
-   Linker
-   ObjectCode
-   Kernel
-
-   :template: dataclass.rst
-
-   ProgramOptions
-   LinkerOptions
-
-Program caches
-``````````````
-
-``Program.compile`` accepts a ``cache=`` keyword argument that integrates
-with any :class:`~cuda.core.utils.ProgramCacheResource`, so callers can
-avoid recompiling identical source + options + target without writing the
-:func:`~cuda.core.utils.make_program_cache_key` lookup by hand.
-
-.. currentmodule:: cuda.core.utils
-
-.. autosummary::
-   :toctree: generated/
-
-   ProgramCacheResource
-   InMemoryProgramCache
-   FileStreamProgramCache
-   make_program_cache_key
-
-.. currentmodule:: cuda.core
-
-
 CUDA process checkpointing
 --------------------------
 
@@ -303,6 +307,8 @@ Use ``Process.restore_thread_id`` to discover that thread before calling
 persistence mode to be enabled or ``cuInit`` to have been called before
 execution.
 
+.. currentmodule:: cuda.core
+
 .. autosummary::
    :toctree: generated/
 
@@ -314,6 +320,8 @@ execution.
 Utility functions
 -----------------
 
+.. currentmodule:: cuda.core
+
 .. autosummary::
    :toctree: generated/
 

diff --git a/cuda_core/docs/source/release/1.1.0-notes.rst b/cuda_core/docs/source/release/1.1.0-notes.rst
@@ -7,13 +7,33 @@
 =================================
 
 
+Highlights
+----------
+
+- ``cuda.core`` now ships with ``.pyi`` type stubs for all public APIs,
+  giving IDEs and type checkers full autocompletion and static analysis.
+- New :mod:`cuda.core.texture` module for texture and surface memory:
+  :class:`~texture.OpaqueArray`, :class:`~texture.MipmappedArray`,
+  :class:`~texture.TextureObject`, and :class:`~texture.SurfaceObject`,
+  constructed through the corresponding ``Device.create_*`` factories.
+- Richer managed-memory support: the new :class:`ManagedBuffer` exposes a
+  property-style advice API (:attr:`~ManagedBuffer.read_mostly`,
+  :attr:`~ManagedBuffer.preferred_location`,
+  :attr:`~ManagedBuffer.accessed_by`) with NUMA-aware host locations via the
+  new :class:`Host` type, plus batched range operations in
+  :mod:`cuda.core.utils` for prefetching and discarding many buffers at once.
+- CUDA 13.3 toolkit support.
+  (`#2139 <https://github.com/NVIDIA/cuda-python/pull/2139>`__)
+
+
 New features
 ------------
 
 - Added :class:`Host` as the symmetric counterpart of :class:`Device` for
   expressing managed-memory locations: ``Host()`` (any host),
   ``Host(numa_id=N)`` (specific NUMA node), and ``Host.numa_current()``
   (calling thread's NUMA node).
+  (`#1775 <https://github.com/NVIDIA/cuda-python/pull/1775>`__)
 
 - Added :class:`ManagedBuffer`, a :class:`Buffer` subclass returned by
   :meth:`ManagedMemoryResource.allocate` that exposes a property-style
@@ -30,13 +50,16 @@ New features
 
   Use :meth:`ManagedBuffer.from_handle` to wrap an existing managed-memory
   pointer.
+  (`#1775 <https://github.com/NVIDIA/cuda-python/pull/1775>`__)
 
 - Added batched managed-memory range operations to :mod:`cuda.core.utils`
   (CUDA 13+): :func:`~utils.prefetch_batch`, :func:`~utils.discard_batch`,
   and :func:`~utils.discard_prefetch_batch`. Each takes a sequence of
   managed :class:`Buffer` instances and dispatches to the corresponding
   ``cuMem*BatchAsync`` driver entry point, addressing the managed-memory
-  portion of #1333. Single-buffer operations are exposed as instance
+  portion of
+  `#1333 <https://github.com/NVIDIA/cuda-python/issues/1333>`__. Single-buffer
+  operations are exposed as instance
   methods on :class:`ManagedBuffer` (:meth:`~ManagedBuffer.prefetch`,
   :meth:`~ManagedBuffer.discard`, :meth:`~ManagedBuffer.discard_prefetch`)
   and as property setters (:attr:`~ManagedBuffer.read_mostly`,
@@ -48,28 +71,103 @@ New features
   :meth:`system.Device.get_nvlinks` for device-specific NVLink enumeration.
   These APIs avoid relying on the static NVML ``NVML_NVLINK_MAX_LINKS`` macro
   when querying the links available on a particular device.
+  (`#2192 <https://github.com/NVIDIA/cuda-python/pull/2192>`__)
 
 - Added the :attr:`graph.GraphBuilder.graph_definition` property, which
   exposes a captured graph as an explicit :class:`graph.GraphDefinition`
   view sharing ownership of the same underlying graph. This enables hybrid
   flows that mix the capture and explicit graph-building APIs, such as
   inspecting or augmenting a captured graph, or populating a conditional
   body entirely through the explicit API.
+  (`#2026 <https://github.com/NVIDIA/cuda-python/pull/2026>`__)
+
+- Added the :mod:`cuda.core.texture` module for texture and surface memory:
+  :class:`~texture.OpaqueArray` and :class:`~texture.MipmappedArray` for
+  hardware-laid-out array allocations, and :class:`~texture.TextureObject` and
+  :class:`~texture.SurfaceObject` for bindless kernel-side sampled reads and
+  typed load/store. Objects are constructed from a
+  :class:`~texture.ResourceDescriptor` via
+  :meth:`Device.create_opaque_array`, :meth:`Device.create_mipmapped_array`,
+  :meth:`Device.create_texture_object`, and :meth:`Device.create_surface_object`.
+  (`#467 <https://github.com/NVIDIA/cuda-python/issues/467>`__,
+  `#2095 <https://github.com/NVIDIA/cuda-python/pull/2095>`__,
+  `#2307 <https://github.com/NVIDIA/cuda-python/pull/2307>`__)
 
 - ``cuda.core`` now ships with ``.pyi`` stubs for all public APIs, enabling
   users' IDEs and type checkers to provide better autocompletion and static
   analysis.
+  (`#2061 <https://github.com/NVIDIA/cuda-python/pull/2061>`__)
+
+- :class:`ObjectCode` and :class:`Program` now accept path-like inputs in
+  addition to strings and bytes.
+  (`#2123 <https://github.com/NVIDIA/cuda-python/pull/2123>`__)
+
+- Exposed a :attr:`Buffer.size` accessor to Python.
+  (`#2068 <https://github.com/NVIDIA/cuda-python/pull/2068>`__,
+  closes `#2049 <https://github.com/NVIDIA/cuda-python/issues/2049>`__)
 
-Bug fixes
----------
+Fixes and enhancements
+----------------------
 
 - On WSL, ``cuda.core.system.get_process_name`` would raise a
   ``UnicodeDecodeError``.  It should now return the correct result.
+  (`#2118 <https://github.com/NVIDIA/cuda-python/pull/2118>`__)
 - Calling ``cuda.core.system.get_process_name`` before querying any device's
   ``compute_running_processes`` would raise a ``NvmlNotFoundError``.  Now it will
   correctly return the process name, if it is a GPU-using process.
 - :meth:`system.Device.get_nvlink` now validates link numbers against the
   device-specific NVLink count and raises ``ValueError`` for unsupported links.
+  (`#2192 <https://github.com/NVIDIA/cuda-python/pull/2192>`__)
+- Hardened the IPC buffer import path against malformed or untrusted peer
+  descriptors: descriptor payloads shorter than the driver struct are now
+  rejected before import
+  (`#2223 <https://github.com/NVIDIA/cuda-python/pull/2223>`__), an imported
+  buffer's size is validated against the mapped allocation extent before any
+  copy (`#2224 <https://github.com/NVIDIA/cuda-python/pull/2224>`__), and
+  negative allocation handles are always rejected, including under ``-O``
+  (`#2219 <https://github.com/NVIDIA/cuda-python/pull/2219>`__).
+- :attr:`ManagedBuffer.accessed_by` now validates every location before
+  issuing any advice, so a bulk assignment containing an invalid entry can no
+  longer leave the applied advice in a torn state.
+  (`#2222 <https://github.com/NVIDIA/cuda-python/pull/2222>`__)
+- Graph nodes now keep their Python-owned attachments (kernel-argument
+  buffers, host-callback functions and user data, and memcpy/memset operands)
+  alive for the lifetime of the graph. Previously, keeping these objects alive
+  was the caller's responsibility.
+  (`#2280 <https://github.com/NVIDIA/cuda-python/pull/2280>`__)
+- Hardened the graph user-object destructor against races during Python
+  interpreter shutdown.
+  (`#2074 <https://github.com/NVIDIA/cuda-python/pull/2074>`__)
+- Free-threading correctness fixes: buffer and memory-resource threading
+  (`#2162 <https://github.com/NVIDIA/cuda-python/pull/2162>`__), critical-section
+  guards on shared accessors
+  (`#2215 <https://github.com/NVIDIA/cuda-python/pull/2215>`__), and an atomic
+  flag guarding buffer memory-attribute initialization
+  (`#2216 <https://github.com/NVIDIA/cuda-python/pull/2216>`__).
+- :meth:`Program.compile` cache keys are now FIPS-safe.
+  (`#2087 <https://github.com/NVIDIA/cuda-python/pull/2087>`__)
+- Memory-pool driver errors are now preserved instead of being masked by
+  out-of-memory handling.
+  (`#2084 <https://github.com/NVIDIA/cuda-python/pull/2084>`__)
+- DLPack export now raises ``BufferError`` (the intended exception) instead of
+  ``RuntimeError`` when a buffer cannot be exported.
+  (`#2160 <https://github.com/NVIDIA/cuda-python/pull/2160>`__)
+- Corrected the :class:`Buffer` and :class:`MemoryResource` ``__eq__``
+  implementations.
+  (`#2067 <https://github.com/NVIDIA/cuda-python/pull/2067>`__,
+  closes `#2050 <https://github.com/NVIDIA/cuda-python/issues/2050>`__)
+- Checkpoint restore now validates GPU UUID inputs early.
+  (`#2086 <https://github.com/NVIDIA/cuda-python/pull/2086>`__)
+- Bumped the PyTorch tensor-bridge upper bound to 2.12.
+  (`#2099 <https://github.com/NVIDIA/cuda-python/pull/2099>`__)
+
+Documentation
+-------------
+
+- Documented the IPC buffer pickle trust boundary: :meth:`Buffer.__reduce__`
+  and multi-process IPC users should review the security note before
+  unpickling buffer handles from untrusted sources.
+  (`#2225 <https://github.com/NVIDIA/cuda-python/pull/2225>`__)
 
 Deprecated APIs
 ---------------