EP documentation updates #6253
Merged
EP documentation updates #6253
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
edgchen1
requested review from
faxu,
jywu-msft,
manashgoswami,
natke and
pranavsharma
jywu-msft
reviewed
Jan 5, 2021
|
|
||
| # CUDA Execution Provider | ||
|
|
||
| The CUDA Execution Provider enables hardware accelerated computation on CUDA-enabled GPUs. |
Member
There was a problem hiding this comment.
"computation on Nvidia GPUs" might be better? #Resolved
jywu-msft
reviewed
Jan 5, 2021
| For build instructions, please see the [BUILD page](../../how-to/build.md#CUDA). | ||
|
|
||
| ## Configuration Options | ||
| The CUDA EP supports the following configuration options: |
Member
There was a problem hiding this comment.
would it be possible to link to some sample usage in C++/python etc. ? #Resolved
pranavsharma
reviewed
Jan 5, 2021
| The device ID. | ||
|
|
||
| ### cuda_mem_limit | ||
| The memory limit of the device memory arena in bytes. |
Contributor
There was a problem hiding this comment.
This might need more clarification based on this question #6215. #Resolved
jywu-msft
approved these changes
Jan 6, 2021
hariharans29
reviewed
Jan 7, 2021
hariharans29
reviewed
Jan 7, 2021
hariharans29
reviewed
Jan 7, 2021
hariharans29
reviewed
Jan 8, 2021
| The device ID. | ||
|
|
||
| ### cuda_mem_limit | ||
| The size limit of the device memory arena in bytes. This size limit is only for the execution provider's arena. The total device memory usage may be higher. |
Member
There was a problem hiding this comment.
Sorry for adding another comment. Maybe it is worth specifying the "default" values for each of these parameters ? For example, reading the doc, I understand what the valid values for cudnn_conv_algo_search are and what each option means. What is hard to parse is the "default" value for each. #Resolved
hariharans29
approved these changes
Jan 9, 2021
natke
approved these changes
Jan 12, 2021
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Add some initial documentation for the CUDA EP with some details about configuration options.
Update Nuphar EP documentation usage of deprecated set_nuphar_settings() function.
Motivation and Context
Needed somewhere to document CUDA EP provider-specific options.
Deprecation of Python global configuration functions.