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 4, 02:30 UTC
[CI] Narrow misc.yaml source dependencies (#42059)
Signed-off-by: khluu <khluu000@gmail.com>
Kevin H. Luu committed
May 8, 2026 at 15:10 UTC
0c2e9d48927f8122cba25f9a649a72f131faffb3
1 file changed
+112
-8
.buildkite/test_areas/misc.yaml
+112
-8
@@ -6,7 +6,15 @@ steps:
6
key: v1-spec-decode
7
timeout_in_minutes: 30
8
source_file_dependencies:
9
- - vllm/
9
+ - vllm/config/
10
+ - vllm/distributed/
11
+ - vllm/inputs/
12
+ - vllm/model_executor/
13
+ - vllm/platforms/
14
+ - vllm/sampling_params.py
15
+ - vllm/transformers_utils/
16
+ - vllm/utils/
17
+ - vllm/v1/
18
- tests/v1/spec_decode
19
commands:
20
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
@@ -18,7 +26,17 @@ steps:
26
timeout_in_minutes: 30
27
device: h200_18gb
28
source_file_dependencies:
21
- - vllm/
29
+ - vllm/config/
30
+ - vllm/distributed/
31
+ - vllm/engine/
32
+ - vllm/inputs/
33
+ - vllm/logger.py
34
+ - vllm/model_executor/
35
+ - vllm/platforms/
36
+ - vllm/sampling_params.py
37
+ - vllm/transformers_utils/
38
+ - vllm/utils/
39
+ - vllm/v1/
40
- tests/v1/sample
41
- tests/v1/logits_processors
42
- tests/v1/test_oracle.py
@@ -41,7 +59,23 @@ steps:
59
key: v1-core-kv-metrics
60
timeout_in_minutes: 30
61
source_file_dependencies:
44
- - vllm/
62
+ - vllm/config/
63
+ - vllm/distributed/
64
+ - vllm/engine/
65
+ - vllm/entrypoints/pooling/
66
+ - vllm/inputs/
67
+ - vllm/lora/
68
+ - vllm/model_executor/
69
+ - vllm/multimodal/
70
+ - vllm/outputs.py
71
+ - vllm/platforms/
72
+ - vllm/pooling_params.py
73
+ - vllm/profiler/
74
+ - vllm/sampling_params.py
75
+ - vllm/tokenizers/
76
+ - vllm/transformers_utils/
77
+ - vllm/utils/
78
+ - vllm/v1/
79
- tests/v1/core
80
- tests/v1/executor
81
- tests/v1/kv_offload
@@ -68,7 +102,21 @@ steps:
102
depends_on:
103
- image-build-cpu
104
source_file_dependencies:
71
- - vllm/
105
+ - vllm/config/
106
+ - vllm/distributed/
107
+ - vllm/engine/
108
+ - vllm/inputs/
109
+ - vllm/lora/
110
+ - vllm/multimodal/
111
+ - vllm/outputs.py
112
+ - vllm/platforms/
113
+ - vllm/pooling_params.py
114
+ - vllm/profiler/
115
+ - vllm/sampling_params.py
116
+ - vllm/tokenizers/
117
+ - vllm/transformers_utils/
118
+ - vllm/utils/
119
+ - vllm/v1/
120
- tests/v1
121
device: cpu-small
122
commands:
@@ -84,7 +132,17 @@ steps:
132
timeout_in_minutes: 20
133
device: h200_18gb
134
source_file_dependencies:
87
- - vllm/
135
+ - vllm/config/
136
+ - vllm/distributed/
137
+ - vllm/engine/
138
+ - vllm/inputs/
139
+ - vllm/model_executor/
140
+ - vllm/multimodal/
141
+ - vllm/platforms/
142
+ - vllm/sampling_params.py
143
+ - vllm/transformers_utils/
144
+ - vllm/utils/
145
+ - vllm/v1/
146
- tests/test_regression
147
commands:
148
- pip install modelscope
@@ -128,7 +186,18 @@ steps:
186
timeout_in_minutes: 20
187
num_devices: 2
188
source_file_dependencies:
131
- - vllm/
189
+ - vllm/config/
190
+ - vllm/distributed/
191
+ - vllm/engine/
192
+ - vllm/inputs/
193
+ - vllm/model_executor/
194
+ - vllm/multimodal/
195
+ - vllm/platforms/
196
+ - vllm/sampling_params.py
197
+ - vllm/tracing/
198
+ - vllm/transformers_utils/
199
+ - vllm/utils/
200
+ - vllm/v1/
201
- tests/v1/tracing
202
commands:
203
- "pip install \
@@ -152,7 +221,19 @@ steps:
221
key: async-engine-inputs-utils-worker
222
timeout_in_minutes: 50
223
source_file_dependencies:
155
- - vllm/
224
+ - vllm/assets/
225
+ - vllm/config/
226
+ - vllm/distributed/
227
+ - vllm/engine/
228
+ - vllm/inputs/
229
+ - vllm/model_executor/
230
+ - vllm/multimodal/
231
+ - vllm/platforms/
232
+ - vllm/sampling_params.py
233
+ - vllm/tokenizers/
234
+ - vllm/transformers_utils/
235
+ - vllm/utils/
236
+ - vllm/v1/
237
- tests/detokenizer
238
- tests/multimodal
239
- tests/utils_
@@ -167,7 +248,30 @@ steps:
248
- image-build-cpu
249
timeout_in_minutes: 30
250
source_file_dependencies:
170
- - vllm/
251
+ - vllm/assets/
252
+ - vllm/config/
253
+ - vllm/engine/arg_utils.py
254
+ - vllm/entrypoints/chat_utils.py
255
+ - vllm/entrypoints/mcp/
256
+ - vllm/entrypoints/openai/chat_completion/protocol.py
257
+ - vllm/entrypoints/openai/engine/protocol.py
258
+ - vllm/envs.py
259
+ - vllm/exceptions.py
260
+ - vllm/inputs/
261
+ - vllm/model_executor/layers/quantization/quark/
262
+ - vllm/multimodal/
263
+ - vllm/outputs.py
264
+ - vllm/platforms/
265
+ - vllm/pooling_params.py
266
+ - vllm/ray/
267
+ - vllm/reasoning/
268
+ - vllm/renderers/
269
+ - vllm/sampling_params.py
270
+ - vllm/tokenizers/
271
+ - vllm/tool_parsers/
272
+ - vllm/transformers_utils/
273
+ - vllm/utils/
274
+ - vllm/v1/
275
- tests/test_inputs.py
276
- tests/test_outputs.py
277
- tests/test_pooling_params.py