Implement PageAllocation as a handle into a PagedAttentionCache, allowing publishing and releasing an allocation via handle rather than cache #608
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
This was referenced Nov 26, 2024
renxida
force-pushed
the
page-allocation-handle
branch
from
00e608d to
82eafe2
Compare
stbaione
reviewed
Nov 26, 2024
shortfin/python/shortfin_apps/llm/components/kvcache/base_attention_cache.py
Outdated
Show resolved
Hide resolved
stbaione
reviewed
Nov 26, 2024
shortfin/python/shortfin_apps/llm/components/kvcache/base_attention_cache.py
Outdated
Show resolved
Hide resolved
stbaione
reviewed
Nov 26, 2024
|
A couple small comments on form, but functionally, this looks great. There are a decent bit of changes in critical areas, so some unit tests might be nice to include before merging |
renxida
force-pushed
the
page-allocation-handle
branch
from
d5a8073 to
1a844ec
Compare
renxida
force-pushed
the
page-allocation-handle
branch
from
4563776 to
2edccfd
Compare
renxida
changed the title
renxida
force-pushed
the
page-allocation-handle
branch
from
2edccfd to
e27b695
Compare
renxida
force-pushed
the
page-allocation-handle
branch
from
e27b695 to
0966bbe
Compare
stbaione
approved these changes
Dec 2, 2024
renxida
force-pushed
the
page-allocation-handle
branch
from
0966bbe to
d0a77e2
Compare
renxida
force-pushed
the
page-allocation-handle
branch
from
d0a77e2 to
7371ba8
Compare
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Outdated suggestions cannot be applied.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.
Deinitialization looks wonky for now. Will test extensively to get deinit right once I merge #600
Closes #607