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

[Feature] Support Decode Context Parallel (DCP) for MLA (#23734)

Browse Source 
Signed-off-by: hongchao <hongchao@msh.team>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: hongchao <hongchao@msh.team>
Co-authored-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
yzds
2025-09-06 13:24:05 +08:00
committed by GitHub
parent 3c529fc994
commit ac201a0eaf
27 changed files with 999 additions and 230 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.buildkite/test-pipeline.yaml
View File

@@ -837,7 +837,7 @@ steps:
- pytest -v -s models/test_oot_registration.py # it needs a clean process
- pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins
- label: Pipeline Parallelism Test # 45min
- label: Pipeline + Context Parallelism Test # 45min
timeout_in_minutes: 60
mirror_hardwares: [amdexperimental]
working_dir: "/vllm-workspace/tests"
@@ -851,6 +851,7 @@ steps:
commands:
- pytest -v -s distributed/test_pp_cudagraph.py
- pytest -v -s distributed/test_pipeline_parallel.py
# - pytest -v -s distributed/test_context_parallel.py # TODO: enable it on Hopper runners or add triton MLA support
- label: LoRA TP Test (Distributed) # 17 min
timeout_in_minutes: 30