Extending TGI benchmarking and documentation #621
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
dacorvo
reviewed
Jun 4, 2024
benchmark/text-generation-inference/llama3-70b-inf2.48xlarge/.env
Outdated
Show resolved
Hide resolved
benchmark/text-generation-inference/llama3-70b-inf2.48xlarge/docker-compose.yaml
Outdated
Show resolved
Hide resolved
benchmark/text-generation-inference/llama3-70b-inf2.48xlarge/tgi-results-batchsize-1.csv
Show resolved
Hide resolved
benchmark/text-generation-inference/llama3-70b-trn1.32xlarge/docker-compose.yaml
Outdated
Show resolved
Hide resolved
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Co-authored-by: David Corvoysier <david.corvoysier@gmail.com>
dacorvo
reviewed
Jun 4, 2024
HF_SEQUENCE_LENGTH settings from .env and docker compose.
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Outdated suggestions cannot be applied.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.
This PR extends the Readme for TGI benchmarking and adds additional benchmarks.
It includes:
-A note about downloading and tagging TGI image if you aren't building it locally(discussed with @dacorvo in #605 )
-Llama3-70B example on both Inferentia and Trainium.
-instructions on how to compile models not available in the hub (e.g. 32 core Llama3-70B)
-A run_all.sh script that will generate benchmarks for different concurrencies. (if there is an easier way to do this, like passing a list into the benchmark.sh script, I don't know how).
-Does not change the existing examples in case you are using them for any TGI tests.
-Adds some batch size=one metrics
Before submitting