[Profiling][Model][Doc] Support Llama3-8B and 70B on A100s #22
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
…100_pairwise_nvlink # Changelog * Support Llama3 8B and 70B https://llama.meta.com/llama3/ * Max supported context length is 32k, only on 4xA100. * Pipeline parallel is not profiled yet for more than 4k. * Attention profiling enhancements: ** Reduce number of input combinations by removing those batches which require more kv cache blocks than available GPU memory.
Hanchenli
pushed a commit
to XbzOnGit/vidur
that referenced
this pull request
Nov 8, 2024
) * Merged PR 1873: Support Llama3 8B and 70B for 32k context length on a100_pairwise_nvlink # Changelog * Support Llama3 8B and 70B https://llama.meta.com/llama3/ * Max supported context length is 32k, only on 4xA100. * Pipeline parallel is not profiled yet for more than 4k. * Attention profiling enhancements: ** Reduce number of input combinations by removing those batches which require more kv cache blocks than available GPU memory. * Fix llama3-8B and 70B profiling data * Bring documentation files to top-level docs/ folder * Add llama3-70b attention profiling data * format * minor
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Outdated suggestions cannot be applied.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 adds support for Llama3-8B and Llama3-70B on A100s upto 16k context length 🎉
Earlier models were supported upto 4k context length. Refactored the attention profiling module to complete attention profiling for 16k context in 30mins on 4 A100s instead of several hours.
PR Checklist (Click to Expand)
Thank you for your contribution to Vidur! Before submitting the pull request, please ensure the PR meets the following criteria. This helps Vidur maintain the code quality and improve the efficiency of the review process.
PR Title and Classification
Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:
[Bugfix]for bug fixes.[CI/Build]for build or continuous integration improvements.[Doc]for documentation fixes and improvements.[Model]for adding a new model or improving an existing model. Model name should appear in the title.[Profiling]For changes on the profiling module.[Core]for changes in the core simulator logic[Misc]for PRs that do not fit the above categories. Please use this sparingly.Note: If the PR spans more than one category, please include all relevant prefixes.
Code Quality
The PR need to meet the following code quality standards:
make formatto format your code.docs/source/if the PR modifies the user-facing behaviors of Vidur. It helps user understand and utilize the new features or changes.Notes for Large Changes
Please keep the changes as concise as possible. For major architectural changes (>500 LOC), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with
rfc-requiredand might not go through the PR.Thank You
Finally, thank you for taking the time to read these guidelines and for your interest in contributing to Vidur. Your contributions make Vidur a great tool for everyone!