Fix llama fp8 benchmark test and remove decomposed benchmarking tests #1000
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
aviator19941
requested review from
archana-ramalingam,
dan-garvey,
sogartar and
AmosLewis
archana-ramalingam
approved these changes
Feb 25, 2025
There was a problem hiding this comment.
For the pre-submit llama benchmark test failure, it uses pinned IREE, which needs to be bumped to 3.3.0rc20250219 version that includes the fix for this error.
aviator19941
force-pushed
the
fix_llama_fp8_benchmark_test
branch
4 times, most recently
from
57da45e to
62e71c1
Compare
aviator19941
force-pushed
the
fix_llama_fp8_benchmark_test
branch
2 times, most recently
from
9aa32b9 to
5c2c4f8
Compare
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
…, update 8b fp8 test and weight paths Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
…a follow-up PR Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
Signed-off-by: aviator19941 <[email protected]>
monorimet
pushed a commit
that referenced
this pull request
Mar 5, 2025
…#1000) Fixes llama fp8 benchmark test, updates the prefill and decode paths, and removes decomposed benchmarking tests. --------- Signed-off-by: aviator19941 <[email protected]>
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.
Fixes llama fp8 benchmark test, updates the prefill and decode paths, and removes decomposed benchmarking tests.