Skip to content
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

[Core] Fix edge case in chunked prefill + block manager v2 #7380

Merged
merged 2 commits into from
Aug 9, 2024
Merged

[Core] Fix edge case in chunked prefill + block manager v2 #7380

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cf718b0
Fix edge case in chunked prefill + block manager v2
cadedaniel Aug 9, 2024
f19d2f8
format
cadedaniel Aug 9, 2024
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
18 changes: 15 additions & 3 deletions tests/core/block/e2e/test_correctness.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,11 +261,22 @@ def test_lookahead_greedy_equality_with_preemption(baseline_llm_generator,
# skip cuda graph creation for fast test.
"enforce_eager": True,
"enable_chunked_prefill": True,
"max_num_batched_tokens": 2,
"max_num_seqs": 2,
},
])
@pytest.mark.parametrize("per_test_common_llm_kwargs", [{}])
@pytest.mark.parametrize("per_test_common_llm_kwargs",
[{
"block_size": 8,
"max_num_batched_tokens": 2,
"max_num_seqs": 2,
}, {
"block_size": 8,
"max_num_batched_tokens": 3,
"max_num_seqs": 2,
}, {
"block_size": 8,
"max_num_batched_tokens": 256,
"max_num_seqs": 10,
}])
@pytest.mark.parametrize("baseline_llm_kwargs", [
{
"use_v2_block_manager": False,
Expand Down Expand Up @@ -294,6 +305,7 @@ def test_chunked_prefill_block_manager_v2(baseline_llm_generator,
prompts = [
"Hello, my name is",
"The president of the United States is",
("1 + " * 50) + " 1 = ", # Longer prompt.
"The capital of France is",
"The future of AI is",
]
Expand Down
6 changes: 6 additions & 0 deletions vllm/core/block/block_table.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -356,7 +356,13 @@ def _chunk_token_blocks_for_append(
appended to blocks. The first such "token block" may have less token ids
than the block size, since the last allocated block may be partially
full.

If no token ids are provided, then no chunks are returned.
"""

if not token_ids:
return []

first_chunk_size = self._block_size - (self._num_full_slots %
self._block_size)
token_blocks = [token_ids[:first_chunk_size]]
Expand Down
Loading