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 16, 10:45 UTC
[ci] Add CODEOWNERS for test directories (#8795)
Signed-off-by: kevin <kevin@anyscale.com>
Kevin H. Luu committed
Sep 30, 2024 at 17:47 UTC
1425a1bcf9c53e24fe5f4812acc5b656f2aa02f3
2 files changed
+29
-2
.buildkite/test-pipeline.yaml
+10
-2
@@ -64,13 +64,21 @@ steps:
64
fast_check: true
65
source_file_dependencies:
66
- vllm/
67
- - tests/basic_correctness
67
+ - tests/basic_correctness/test_basic_correctness
68
+ - tests/basic_correctness/test_cpu_offload
69
+ - tests/basic_correctness/test_preemption
70
commands:
71
- pytest -v -s basic_correctness/test_basic_correctness.py
72
- pytest -v -s basic_correctness/test_cpu_offload.py
73
+ - VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py
74
+
75
+- label: Chunked Prefill Test
76
+ source_file_dependencies:
77
+ - vllm/
78
+ - tests/basic_correctness/test_chunked_prefill
79
+ commands:
80
- VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_chunked_prefill.py
81
- VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_chunked_prefill.py
73
- - VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py
82
83
- label: Core Test # 10min
84
mirror_hardwares: [amd]
.github/CODEOWNERS
new
+19
@@ -0,0 +1,19 @@
1
+# See https://help.github.com/articles/about-codeowners/
2
+# for more info about CODEOWNERS file
3
+
4
+/tests/async_engine @njhill @robertgshaw2-neuralmagic @simon-mo
5
+/tests/test_inputs.py @DarkLight1337 @ywang96
6
+/tests/entrypoints @DarkLight1337 @robertgshaw2-neuralmagic @simon-mo
7
+/tests/models @DarkLight1337 @ywang96
8
+/tests/multimodal @DarkLight1337 @ywang96
9
+/tests/prefix_caching @comaniac @KuntaiDu
10
+/tests/spec_decode @njhill @LiuXiaoxuanPKU
11
+/tests/kernels @tlrmchlsmth @WoosukKwon
12
+/tests/quantization @mgoin @robertgshaw2-neuralmagic
13
+/.buildkite/lm-eval-harness @mgoin @simon-mo
14
+/tests/distributed/test_multi_node_assignment.py @youkaichao
15
+/tests/distributed/test_pipeline_parallel.py @youkaichao
16
+/tests/distributed/test_same_node.py @youkaichao
17
+/tests/multi_step @alexm-neuralmagic @SolitaryThinker @comaniac
18
+/tests/weight_loading @mgoin @youkaichao
19
+/tests/basic_correctness/test_chunked_prefill @rkooo567 @comaniac