Update nightly llama benchmarking tests #754
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
Signed-off-by: aviator19941 <avinash.sharma@amd.com>
Signed-off-by: aviator19941 <avinash.sharma@amd.com>
Signed-off-by: aviator19941 <avinash.sharma@amd.com>
Signed-off-by: aviator19941 <avinash.sharma@amd.com>
ScottTodd
reviewed
Jan 6, 2025
IanNod
approved these changes
Jan 7, 2025
monorimet
pushed a commit
that referenced
this pull request
Jan 8, 2025
- Updates nightly llama benchmarking tests to benchmark input token lengths of 128 and 2048 for llama 8b, 70b, and 405b. - Switch IREE compile flag from `--iree-hal-target-backends` to `--iree-hal-target-device` TODO: Add 405b decode benchmark calls to 405b fp16 tests when decode is fixed --------- Signed-off-by: aviator19941 <avinash.sharma@amd.com> Co-authored-by: Archana Ramalingam <98564406+archana-ramalingam@users.noreply.github.com> Co-authored-by: archana-ramalingam <archana.ramalingam@amd.com>
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Outdated suggestions cannot be applied.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.
--iree-hal-target-backendsto--iree-hal-target-deviceTODO: Add 405b decode benchmark calls to 405b fp16 tests when decode is fixed