Skip to content

[v1] Introduce KVCacheBlocks as interface between Scheduler and KVCacheManager #17479

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.

Sign up for GitHub

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

Merged
merged 6 commits into from
May 6, 2025
Merged

[v1] Introduce KVCacheBlocks as interface between Scheduler and KVCacheManager #17479

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e484ba9
update test
heheda12345 Apr 30, 2025
579c07a
Merge branch 'main' of github.com:vllm-project/vllm into kv_cache_blocks
heheda12345 May 1, 2025
93b985c
cls
heheda12345 May 6, 2025
4f1c40a
rename
heheda12345 May 6, 2025
986f19c
Merge branch 'main' of github.com:vllm-project/vllm into kv_cache_blocks
heheda12345 May 6, 2025
7789dac
fix
heheda12345 May 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions tests/v1/core/test_kv_cache_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -542,7 +542,7 @@ def test_allocate_with_lookahead():
num_tokens=3,
num_lookahead_tokens=2, # Total required: 3+2=5 tokens
)
assert len(blocks) == 2 # ceil(5/4)=2 blocks
assert len(blocks.blocks) == 2 # ceil(5/4)=2 blocks

# Test case 2: With precomputed blocks
kv_cache_manager = KVCacheManager(kv_cache_config=config,
Expand All @@ -553,7 +553,7 @@ def test_allocate_with_lookahead():
num_tokens=3,
num_lookahead_tokens=2,
)
assert len(blocks) == 2
assert len(blocks.blocks) == 2

# Test case 3: With precomputed blocks
# required_blocks = ceil((3 + 4) / 4) = 2
Expand All @@ -564,4 +564,4 @@ def test_allocate_with_lookahead():
num_tokens=3,
num_lookahead_tokens=4,
)
assert len(blocks) == 2
assert len(blocks.blocks) == 2
Loading