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

[Core/DBO][2/N] Dual-Batch Overlap add DeepEP High Throughput support and Prefill support (#24845)

Browse Source 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson
2025-09-23 12:02:10 -04:00
committed by GitHub
parent a903669e10
commit cc1dc7ed6d
19 changed files with 602 additions and 236 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/v1/spec_decode/test_eagle.py
View File

@@ -532,9 +532,8 @@ 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_builders = [
proposer.runner.attn_groups[0][0].get_metadata_builder.return_value = \
attn_metadata_builder
]
result = proposer.propose(target_token_ids=target_token_ids,
target_positions=target_positions,
@@ -659,9 +658,8 @@ 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_builders = [
proposer.runner.attn_groups[0][0].get_metadata_builder.return_value = \
attn_metadata_builder
]
# Setup inputs for the proposer.
target_token_ids = torch.randint(0,