A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 6, 04:30 UTC
[CI] split Entrypoints Integration (API Server 1) into 3 jobs (#37882)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Kunshang Ji committed
Mar 24, 2026 at 01:37 UTC
91fd695b758c56b22835a943d13594e353daeb7c
1 file changed
+31
-3
.buildkite/test_areas/entrypoints.yaml
+31
-3
@@ -25,8 +25,8 @@ steps:
25
- pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
26
- pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
27
28
-- label: Entrypoints Integration (API Server 1)
29
- timeout_in_minutes: 130
28
+- label: Entrypoints Integration (API Server openai - Part 1)
29
+ timeout_in_minutes: 50
30
working_dir: "/vllm-workspace/tests"
31
source_file_dependencies:
32
- vllm/
@@ -34,7 +34,24 @@ steps:
34
- tests/entrypoints/test_chat_utils
35
commands:
36
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
37
- - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/test_multi_api_servers.py
37
+ - pytest -v -s entrypoints/openai/chat_completion --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py
38
+ mirror:
39
+ amd:
40
+ device: mi325_1
41
+ depends_on:
42
+ - image-build-amd
43
+
44
+
45
+- label: Entrypoints Integration (API Server openai - Part 2)
46
+ timeout_in_minutes: 50
47
+ working_dir: "/vllm-workspace/tests"
48
+ source_file_dependencies:
49
+ - vllm/
50
+ - tests/entrypoints/openai
51
+ - tests/entrypoints/test_chat_utils
52
+ commands:
53
+ - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
54
+ - pytest -v -s entrypoints/openai/speech_to_text/
55
- pytest -v -s entrypoints/test_chat_utils.py
56
mirror:
57
amd:
@@ -42,6 +59,17 @@ steps:
59
depends_on:
60
- image-build-amd
61
62
+- label: Entrypoints Integration (API Server openai - Part 3)
63
+ timeout_in_minutes: 50
64
+ working_dir: "/vllm-workspace/tests"
65
+ source_file_dependencies:
66
+ - vllm/
67
+ - tests/entrypoints/openai
68
+ - tests/entrypoints/test_chat_utils
69
+ commands:
70
+ - export VLLM_WORKER_MULTIPROC_METHOD=spawn
71
+ - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/speech_to_text/ --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/test_multi_api_servers.py
72
+
73
- label: Entrypoints Integration (API Server 2)
74
timeout_in_minutes: 130
75
working_dir: "/vllm-workspace/tests"