Added new flag for GPU peer access API control #7261
Merged
Conversation
This file contains 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
nnshah1
reviewed
May 31, 2024
src/command_line_parser.cc
Outdated
| @@ -373,7 +373,8 @@ enum TritonOptionId { | |||
| OPTION_BACKEND_CONFIG, | |||
| OPTION_HOST_POLICY, | |||
| OPTION_MODEL_LOAD_GPU_LIMIT, | |||
| OPTION_MODEL_NAMESPACING | |||
| OPTION_MODEL_NAMESPACING, | |||
| OPTION_PEER_ACCESS | |||
There was a problem hiding this comment.
question - do we gate options based on enable gpu compile flag?
There was a problem hiding this comment.
Looks like we don't gate for GPU right now, although we do it for other build options (e.g. tracing, http, etc).
…-server/server into ibhosale_pinned_mem_fix
Tabrizian
reviewed
May 31, 2024
Tabrizian
reviewed
May 31, 2024
| @@ -777,6 +777,7 @@ SERVER_ARGS="--allow-sagemaker=true --model-control-mode=explicit \ | |||
| --load-model=simple --load-model=ensemble_add_sub_int32_int32_int32 \ | |||
| --load-model=repeat_int32 \ | |||
| --load-model=input_all_required \ | |||
| --load-model=dynamic_batch \ | |||
There was a problem hiding this comment.
Were we missing this model before? Is it correctly added?
There was a problem hiding this comment.
Yes this is a breakage cause by one of my changes in L0_trace.
Tested the pipeline for this change fixes currently failing L0_trace
Co-authored-by: Iman Tabrizian <[email protected]>
Tabrizian
previously approved these changes
May 31, 2024
Tabrizian
approved these changes
Jun 1, 2024
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Outdated suggestions cannot be applied.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.
Added a new flag "--enable-peer-access" at Triton startup to control creation of CUDA context at server startup.
Jira : https://jirasw.nvidia.com/browse/DLIS-6705
Core : triton-inference-server/core#361