Deepseek v2 16b enablement #34
Open
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
lcskrishna
reviewed
Dec 11, 2024
| ramp_func = torch.clamp(linear_func, 0, 1) | ||
| return ramp_func | ||
|
|
||
| class DeepseekV2YarnRotaryEmbedding(DeepseekV2RotaryEmbedding): |
There was a problem hiding this comment.
Can we use YarnRotaryEmbedding from megatron.core.models.common.embeddings.yarn_rotary_pos_embedding instead?
|
@hakankiymaz-amd Could you also make sure the copyright statements are all applied properly? If files are copied over from PAI-megatron-patch without any change, you should keep the original copyright statement there. If it is incorporated with your change, You need to add additional copyright statement for AMD and specify what are the changes. |
|
Copyright statements are added proper to changes from PAI and changes from AMD. |
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Outdated suggestions cannot be applied.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.
Deepseek v2 16b enablement
test_report.csv
MI300X-DeepSeek-V2-Lite-bf16-seq2048-tp1pp1ep8-mbsgbs-ac_sel-do_true-fa_true-sp_true-20241210_173933.log
throughput per GPU: 611.822
All tests passed