Add HPU specific arguments to benchmark_throughput #406
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
benchmarks/benchmark_throughput.py
Outdated
| parser.add_argument("--weights-load-device", | ||
| type=str, | ||
| default=None, | ||
| choices=["cuda", "neuron", "hpu", "cpu"], |
There was a problem hiding this comment.
Why the need to add other than cpu and hpu?
There was a problem hiding this comment.
I didn't want to block other paths that are theoretically possible, based on the EngineArgs defaults. I see that currently this value is based on the DEVICE_OPTIONS, so I can change to this.
michalkuligowski
approved these changes
Oct 22, 2024
michalkuligowski
deleted the
dev/kdamaszke/update-benchmark-throughput
branch
xuechendi
pushed a commit
to xuechendi/vllm-fork
that referenced
this pull request
Oct 23, 2024
Modify `benchmark_throughput.py` to allow running with FP8 on HPU (KV cache dtype `fp8_inc`) and to use padding-aware scheduling.
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Outdated suggestions cannot be applied.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.
Modify
benchmark_throughput.pyto allow running with FP8 on HPU (KV cache dtypefp8_inc) and to use padding-aware scheduling.