Support FP8 KV Cache #652
Merged
Support FP8 KV Cache #652
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
ajtejankar
commented
Oct 19, 2024
tgaddair
reviewed
Oct 25, 2024
server/lorax_server/models/custom_modeling/flash_mistral_modeling.py
Outdated
Show resolved
Hide resolved
tgaddair
reviewed
Oct 25, 2024
server/lorax_server/models/custom_modeling/flash_mistral_modeling.py
Outdated
Show resolved
Hide resolved
tgaddair
reviewed
Oct 25, 2024
server/lorax_server/models/custom_modeling/flash_mistral_modeling.py
Outdated
Show resolved
Hide resolved
tgaddair
reviewed
Oct 25, 2024
tgaddair
reviewed
Oct 25, 2024
tgaddair
reviewed
Oct 25, 2024
|
Suddenly started getting these errors - I am guessing it is because of this merge. Any idea how to resolve ? |
|
Should be fixed with #662 |
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Outdated suggestions cannot be applied.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.
Tested GLUE tasks with and without adapter and the accuracy is as expected. Previous implementation using vllm kernels didn't work in this setting. Uses static scales obtained with ultrachat 2k. The cache is stored in E4M3 format. Test weights at
ajinkya-tejankar/Mistral-7B-Instruct-v0.2-FP8-UltraChat-2000-KV.