Cuda graph #67
Open
Cuda graph #67
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
hogura99
reviewed
Feb 21, 2025
| @@ -280,9 +277,7 @@ def get_args(): | |||
| parser.add_argument("-o", "--output-len", type=int, default=32, help="length of output sequence") | |||
| parser.add_argument("-n", "--num-requests", type=int, default=1000, help="number of requests to generate") | |||
| parser.add_argument("-p", "--profile-dir", type=str, default=None, help="directory to store torch profiler output") | |||
| parser.add_argument("-c", "--cuda-graph", action="store_true", default=False, help="enable cuda graph for all modules") | |||
There was a problem hiding this comment.
Removing this parameter will cause AttributeError in model_config.enable_cuda_graph_attn = args.cuda_graph or args.cuda_graph_attn
There was a problem hiding this comment.
Line 99
DisagMoE/benchmark/benchmark_serving.py
Line 99 in b4713a7
Closed
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Outdated suggestions cannot be applied.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.
Refactor cuda graph execution