biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Core/DBO][1/N] Add Dual-Batch Overlap mechanism to VLLM (#23693)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
This commit is contained in:
Sage Moore
2025-09-16 09:21:48 -07:00
committed by GitHub
parent 08369289af
commit 567939953b
22 changed files with 1257 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/v1/spec_decode/test_eagle.py
View File

@@ -365,7 +365,9 @@ def test_propose(method, attn_backend, num_speculative_tokens, monkeypatch):
# Mock runner for attention metadata building
proposer.runner = mock.MagicMock()
proposer.runner.attn_groups.append([mock.MagicMock()])
proposer.runner.attn_groups[0][0].metadata_builder = attn_metadata_builder
proposer.runner.attn_groups[0][0].metadata_builders = [
attn_metadata_builder
]
result = proposer.propose(target_token_ids=target_token_ids,
target_positions=target_positions,
@@ -489,7 +491,9 @@ def test_propose_tree(spec_token_tree):
# Mock runner for attention metadata building.
proposer.runner = mock.MagicMock()
proposer.runner.attn_groups.append([mock.MagicMock()])
proposer.runner.attn_groups[0][0].metadata_builder = attn_metadata_builder
proposer.runner.attn_groups[0][0].metadata_builders = [
attn_metadata_builder
]
# Setup inputs for the proposer.
target_token_ids = torch.randint(0,