-
Notifications
You must be signed in to change notification settings - Fork 379
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add KV cache for paged/non-paged attention #1355
Open
cyanguwa
wants to merge
124
commits into
NVIDIA:main
Choose a base branch
from
cyanguwa:paged_attention
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
+3,913
−1,192
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
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
for more information, see https://pre-commit.ci
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
for more information, see https://pre-commit.ci
/te-ci pytorch L0 |
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
/te-ci pytorch L0 |
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
for more information, see https://pre-commit.ci
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
8e80771
to
612637c
Compare
Signed-off-by: Charlene Yang <[email protected]>
for more information, see https://pre-commit.ci
Signed-off-by: Charlene Yang <[email protected]>
for more information, see https://pre-commit.ci
/te-ci pytorch L0 |
Signed-off-by: Charlene Yang <[email protected]>
/te-ci pytorch L1 |
/te-ci pytorch L3 |
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
4a2fd47
to
7f1c765
Compare
/te-ci pytorch L0 L1 L3 |
/te-ci jax L0 |
Signed-off-by: Charlene Yang <[email protected]>
/te-ci pytorch L0 |
Signed-off-by: Charlene Yang <[email protected]>
for more information, see https://pre-commit.ci
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
Signed-off-by: Charlene Yang <[email protected]>
for more information, see https://pre-commit.ci
/te-ci pytorch L0 L1 L3 |
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.
Description
This PR adds KV cache support for
FusedAttention
,FlashAttention
, andUnfusedDotProductAttention
backends in TE-PyTorch.bshd
format, and incoming tokens can be inbshd
,sbhd
, orthd
FusedAttention
processes QKV inbshd
,sbhd_2bshd
, orthd_2bshd
format directlyFlashAttention
v2 converts Q tothd
and usesflash_attn_varlen_func
for attentionFlashAttention
v3 (must be 39e7197 or after) converts Q tothd
and usesflash_attn_with_kvcache
for attentionUnfusedDotProductAttention
converts Q tobshd
for attention; for paged, it converts the cache tensors to non-paged first, based on the page tableFusedAttention
andFlashAttention
support CUDA graphfp8_dpa=True
is supported (KV cache is still in FP16/BF16 precision);fp8_mha=True
is notType of change
Changes
Please list the changes introduced in this PR:
Checklist: