[GPU] KV-cache compression support #27114
Draft
+2,970
−232
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
github-actions
bot
added
the
category: transformations
| DynamicQuantize(const Output<Node>& data, | ||
| const QuantizationConfig& config, | ||
| const std::vector<uint64_t>& scales_zp_output_order = {}, | ||
| const bool combine_scales_and_zp = false); |
There was a problem hiding this comment.
I'd suggest adding this interleaved/planar mode for scales and zero points as a part of common operation
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Outdated suggestions cannot be applied.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.
Details:
This PR enables KV-cache compression support
Currently, it supports only combinations of the following configurations:
num_heads * head_sizein a single group) / per-token-per-head (quantization of eachhead_sizegroup for each head per token)Tickets: