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

[Spec Decode][KV Connector] Fix KV transfer in PD + speculative decoding (#35158)

Browse Source 
Signed-off-by: Claude <noreply@anthropic.com>
Signed-off-by: Zhanqiu Hu <zh338@cornell.edu>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
This commit is contained in:
zhanqiuhu
2026-03-06 02:50:44 -05:00
committed by GitHub
parent 807d680337
commit 90f3c01fa4
5 changed files with 484 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
.buildkite/test_areas/distributed.yaml
View File

@@ -213,6 +213,19 @@ steps:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- CROSS_LAYERS_BLOCKS=True bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
- label: NixlConnector PD + Spec Decode acceptance (2 GPUs)
timeout_in_minutes: 30
device: a100
working_dir: "/vllm-workspace/tests"
num_devices: 2
source_file_dependencies:
- vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
- vllm/v1/worker/kv_connector_model_runner_mixin.py
- tests/v1/kv_connector/nixl_integration/
commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- bash v1/kv_connector/nixl_integration/spec_decode_acceptance_test.sh
- label: Pipeline + Context Parallelism (4 GPUs)
timeout_in_minutes: 60
working_dir: "/vllm-workspace/tests"