[E2E] Optimize the E2E test time. (#5294)
### What this PR does / why we need it?
Add cudagraph_capture_sizes for E2E CI test.
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c
Signed-off-by: menogrey <1299267905@qq.com>
This commit is contained in:
@@ -64,6 +64,7 @@ def test_bge_m3_correctness():
|
||||
with VllmRunner(
|
||||
model_name,
|
||||
runner="pooling",
|
||||
cudagraph_capture_sizes=[4],
|
||||
) as vllm_aclgraph_runner:
|
||||
vllm_aclgraph_outputs = vllm_aclgraph_runner.embed(queries)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user