Optimize KV cache dequantization performance#9528
Merged
yaochengji merged 1 commit intopytorch:masterfrom Aug 1, 2025
Merged
Conversation
143e835 to
08adc53
Compare
yaochengji
reviewed
Aug 1, 2025
This change reduces casting of quantized KV cache for best performance.
08adc53 to
6ccf85c
Compare
yaochengji
approved these changes
Aug 1, 2025
Collaborator
yaochengji
left a comment
There was a problem hiding this comment.
LGTM, thanks for the improvement!
Contributor
Author
Thanks! Can you press this PR's merge button for me? |
yaochengji
reviewed
Aug 1, 2025
Contributor
Please ping me if you check in any thing to RPA |
Contributor
Author
ack. will always ping you on an RPA related changes. |
bythew3i
reviewed
Aug 1, 2025
bythew3i
approved these changes
Aug 1, 2025
kyuyeunk
added a commit
to vllm-project/tpu-inference
that referenced
this pull request
Aug 13, 2025
Adds following changes - Add support for query quantization (w8a8) - Optimize performance with KV cache quantization (similar approach in pytorch/xla#9528) Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
kyuyeunk
added a commit
to vllm-project/tpu-inference
that referenced
this pull request
Aug 13, 2025
Adds following changes - Add support for query quantization (w8a8) - Optimize performance of kv cache quantization (similar approach in pytorch/xla#9528) Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
kyuyeunk
added a commit
to vllm-project/tpu-inference
that referenced
this pull request
Aug 13, 2025
Adds following changes - Add support for query quantization (w8a8) - Optimize performance of kv cache quantization (similar approach in pytorch/xla#9528) Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
kyuyeunk
added a commit
to vllm-project/tpu-inference
that referenced
this pull request
Aug 14, 2025
Adds following changes - Add support for query quantization (w8a8) - Optimize performance of kv cache quantization (similar approach in pytorch/xla#9528) Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
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
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.
This change reduces casting of quantized KV cache for best performance.