Skip to content

Commit 26d6268

Browse files
committed
Fix doc syntax
1 parent 37c193d commit 26d6268

3 files changed

Lines changed: 17 additions & 17 deletions

File tree

‎cuda_bindings/cuda/bindings/nvml.pyx‎

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
# SPDX-License-Identifier: Apache-2.0
44
#
55
# This code was automatically generated across versions from 12.9.1 to 13.4.1. Do not modify it directly.
6-
# CYTHON-BINDINGS-GENERATED-DO-NOT-MODIFY-THIS-FILE: format=1; content-sha256=5ed3725c25cf754a1e180ca213be9beed28f8e6fd8852ab22df3c9d62f32a8f5
6+
# CYTHON-BINDINGS-GENERATED-DO-NOT-MODIFY-THIS-FILE: format=1; content-sha256=f40bcf5230303700cb1bc97b46c5ca063fd1e8de3562b1ee412e366f26b1419e
77

88

99
# <<<< PREAMBLE CONTENT >>>>
@@ -28593,7 +28593,7 @@ cpdef init_v2():
2859328593
This will initialize the NVML Library state without enumerating any discovered
2859428594
devices. This will allow NVML to communicate with a device, even if other
2859528595
devices are in an unstable or bad state. Enumeration of a device can be done by
28596-
obtaining the device handle via the nvmlDeviceGetHandleBy\* class of APIs.
28596+
obtaining the device handle via the nvmlDeviceGetHandleBy* class of APIs.
2859728597
This method needs to be called once before any usage of NVML Library APIs.
2859828598
For all products.
2859928599

@@ -28615,14 +28615,14 @@ cpdef init_with_flags(unsigned int flags):
2861528615
A variant of :func:`init_v2`, this will initialize the NVML Library state
2861628616
without enumerating any discovered devices. An option to pass in additional
2861728617
flags is provided to modify the behavior of NVML Library init. The usage of
28618-
these flags can be obtained from NVML_INIT_FLAG_\*. These flags can be combined
28618+
these flags can be obtained from NVML_INIT_FLAG_*. These flags can be combined
2861928619
together.
2862028620
Other than the "flags" parameter, this method is completely identical to
2862128621
:func:`init_v2`.
2862228622
For all products.
2862328623

2862428624
Args:
28625-
flags (unsigned int): NVML_INIT_FLAG_\* flags that can modify NVML
28625+
flags (unsigned int): NVML_INIT_FLAG_* flags that can modify NVML
2862628626
Init behavior.
2862728627

2862828628
.. note::
@@ -30391,7 +30391,7 @@ cpdef unsigned int device_get_temperature_threshold(intptr_t device, int thresho
3039130391
NVML_TEMPERATURE_THRESHOLD_MEM_MAX and NVML_TEMPERATURE_THRESHOLD_GPU_MAX.
3039230392
Support for reading these temperature thresholds for Ada and later
3039330393
architectures would be removed from this API in future releases. Please use
30394-
``nvmlDeviceGetFieldValues`` with NVML_FI_DEV_TEMPERATURE_\* fields to retrieve
30394+
``nvmlDeviceGetFieldValues`` with NVML_FI_DEV_TEMPERATURE_* fields to retrieve
3039530395
temperature thresholds on these architectures.
3039630396

3039730397
Args:
@@ -32410,7 +32410,7 @@ cpdef unsigned int device_get_architecture(intptr_t device) except? 0:
3241032410

3241132411
Returns:
3241232412
unsigned int: Reference where architecture is returned, if call
32413-
successful. Set to NVML_DEVICE_ARCH_\* upon success.
32413+
successful. Set to NVML_DEVICE_ARCH_* upon success.
3241432414

3241532415
.. seealso:: `nvmlDeviceGetArchitecture`
3241632416
"""
@@ -32532,7 +32532,7 @@ cpdef device_set_persistence_mode(intptr_t device, int mode):
3253232532
After calling this API with mode set to NVML_FEATURE_DISABLED on a device that
3253332533
has its own NUMA memory, the given device handle will no longer be valid, and
3253432534
to continue to interact with this device, a new handle should be obtained from
32535-
one of the nvmlDeviceGetHandleBy\*() APIs. This limitation is currently only
32535+
one of the nvmlDeviceGetHandleBy*() APIs. This limitation is currently only
3253632536
applicable to devices that have a coherent NVLink connection to system memory.
3253732537

3253832538
Args:
@@ -33825,7 +33825,7 @@ cpdef str vgpu_type_get_license(unsigned int vgpu_type_id):
3382533825

3382633826
The license type and version required to run the specified vGPU type is
3382733827
returned as an alphanumeric string, in the form "<license name>,<version>", for
33828-
example "GRID-Virtual-PC,2.0". If a vGPU is runnable with\* more than one type
33828+
example "GRID-Virtual-PC,2.0". If a vGPU is runnable with* more than one type
3382933829
of license, the licenses are delimited by a semicolon, for example "GRID-
3383033830
Virtual-PC,2.0;GRID-Virtual-WS,2.0;GRID-Virtual-WS-Ext,2.0".
3383133831
The total length of the returned string will not exceed 128 characters,
@@ -34588,7 +34588,7 @@ cpdef object device_get_vgpu_scheduler_state(intptr_t device):
3458834588

3458934589

3459034590
cpdef object device_get_vgpu_scheduler_capabilities(intptr_t device):
34591-
"""Returns the vGPU scheduler capabilities. The list of supported vGPU schedulers returned in ``nvmlVgpuSchedulerCapabilities_t`` is from the NVML_VGPU_SCHEDULER_POLICY_\*. This list enumerates the supported scheduler policies if the engine is Graphics type. The other values in ``nvmlVgpuSchedulerCapabilities_t`` are also applicable if the engine is Graphics type. For other engine types, it is BEST EFFORT policy. If ARR is supported and enabled, scheduling frequency and averaging factor are applicable else timeSlice is applicable.
34591+
"""Returns the vGPU scheduler capabilities. The list of supported vGPU schedulers returned in ``nvmlVgpuSchedulerCapabilities_t`` is from the NVML_VGPU_SCHEDULER_POLICY_*. This list enumerates the supported scheduler policies if the engine is Graphics type. The other values in ``nvmlVgpuSchedulerCapabilities_t`` are also applicable if the engine is Graphics type. For other engine types, it is BEST EFFORT policy. If ARR is supported and enabled, scheduling frequency and averaging factor are applicable else timeSlice is applicable.
3459234592

3459334593
For Pascal ™️ or newer fully supported devices.
3459434594

@@ -35243,9 +35243,9 @@ cpdef object gpu_instance_get_compute_instance_profile_info_v(intptr_t gpu_insta
3524335243
gpu_instance (intptr_t): The identifier of the target GPU
3524435244
instance.
3524535245
profile (unsigned int): One of the
35246-
NVML_COMPUTE_INSTANCE_PROFILE_\*.
35246+
NVML_COMPUTE_INSTANCE_PROFILE_*.
3524735247
eng_profile (unsigned int): One of the
35248-
NVML_COMPUTE_INSTANCE_ENGINE_PROFILE_\*.
35248+
NVML_COMPUTE_INSTANCE_ENGINE_PROFILE_*.
3524935249

3525035250
Returns:
3525135251
nvmlComputeInstanceProfileInfo_v2_t: Returns detailed profile
@@ -36102,12 +36102,12 @@ cpdef object device_get_gpu_fabric_info_v4(intptr_t device):
3610236102
Returns fabric clique data via ``nvmlGpuFabricInfo_v4_t``. Each entry in the
3610336103
``cliques`` array is a (type, id) pair representing a single clique assignment.
3610436104
The number of valid entries is given by ``numCliques``. Entries are sorted by
36105-
ascending type (NVML_GPU_FABRIC_CLIQUE_TYPE_\*), then by ascending clique id
36105+
ascending type (NVML_GPU_FABRIC_CLIQUE_TYPE_*), then by ascending clique id
3610636106
within each type.
3610736107
On Hopper systems, the driver reports Unicast Pointer and Multicast Pointer
3610836108
cliques. On Blackwell and Rubin, Unicast Logical Endpoint and Multicast Logical
3610936109
Endpoint are additionally reported.
36110-
\*\*View CUDA Toolkit Documentation for a C++ code example\*\*.
36110+
\*\*View CUDA Toolkit Documentation for a C++ code example*\*.
3611136111
For Hopper ™️ or newer fully supported devices.
3611236112

3611336113
Args:

‎cuda_bindings/cuda/bindings/nvvm.pyx‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
# SPDX-License-Identifier: Apache-2.0
44
#
55
# This code was automatically generated across versions from 12.0.1 to 13.4.1. Do not modify it directly.
6-
# CYTHON-BINDINGS-GENERATED-DO-NOT-MODIFY-THIS-FILE: format=1; content-sha256=8462b94704f0e45448922fefa8c2b53cf8fffa18c04c70af4604458a36c6cd58
6+
# CYTHON-BINDINGS-GENERATED-DO-NOT-MODIFY-THIS-FILE: format=1; content-sha256=92a06aa55bccfabc1d5bb1216489bb147dfb71d6e628480128fee207b8f3794f
77

88

99
# <<<< PREAMBLE CONTENT >>>>
@@ -178,7 +178,7 @@ cpdef tuple ir_version():
178178

179179

180180
cpdef intptr_t create_program() except? 0:
181-
"""Create a program, and set the value of its handle to ``\*prog``.
181+
"""Create a program, and set the value of its handle to ``*prog``.
182182
183183
184184
Returns:

‎cuda_bindings/docs/source/module/driver.rst‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
44
.. This code was automatically generated with version 13.4.1. Do not modify it directly.
55
6-
.. CYTHON-BINDINGS-GENERATED-DO-NOT-MODIFY-THIS-FILE: format=1; content-sha256=8fb799afff57074126fc28394dc578e31f2d13bffcbecea17a8e14da87e419c7
6+
.. CYTHON-BINDINGS-GENERATED-DO-NOT-MODIFY-THIS-FILE: format=1; content-sha256=36581a940ea8eab6240dfa90b5b0598bb90a5cfa8364156b1626801c89c39a2d
77
------
88
driver
99
------
@@ -2624,7 +2624,7 @@ Data types used by CUDA driver
26242624
.. autoattribute:: cuda.bindings.driver.CUjit_option.CU_JIT_FALLBACK_STRATEGY
26252625

26262626

2627-
Specifies choice of fallback strategy if matching cubin is not found. Choice is based on supplied :py:obj:`~.CUjit_fallback`. This option cannot be used with cuLink\* APIs as the linker requires exact matches.
2627+
Specifies choice of fallback strategy if matching cubin is not found. Choice is based on supplied :py:obj:`~.CUjit_fallback`. This option cannot be used with cuLink* APIs as the linker requires exact matches.
26282628

26292629
Option type: unsigned int for enumerated type :py:obj:`~.CUjit_fallback`
26302630

0 commit comments

Comments
 (0)