Enable Gemma 2B #75
Merged
Enable Gemma 2B #75
Conversation
This file contains hidden or 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
FanhaiLu1
reviewed
May 10, 2024
|
|
||
| with jax.named_scope("attn_insert_cache"): | ||
| keys, values = cache.update(xk, xv) | ||
| self.env.apply_sharding(keys, axis=1) |
Collaborator
There was a problem hiding this comment.
Any reason to remove the keys, values sharding?
FanhaiLu1
reviewed
May 10, 2024
Collaborator
FanhaiLu1
left a comment
FanhaiLu1
left a comment
There was a problem hiding this comment.
Please fix the lint error:
************* Module benchmarks.analyze_sharegpt
benchmarks/analyze_sharegpt.py:75:19: W0621: Redefining name 'prefill_bucket_size_to_ms' from outer scope (line 56) (redefined-outer-name)
lsy323
approved these changes
May 10, 2024
FanhaiLu1
approved these changes
May 10, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
For Gemma 2B we need to change the shardings because the dimension we usually shard,
num_kv_headshappens to be 1 for Gemma 2B. So we pick a different one to shard.