[Refactor] [3/N] Move tool parser tests and run on CPU (#30693)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

.buildkite/test-amd.yaml

@@ -61,8 +61,8 @@ steps:
   - pytest -v -s -m 'not cpu_test' multimodal
   - pytest -v -s utils_
 
-- label: Async Engine, Inputs, Utils, Worker, Config Test (CPU) # 15min
+- label: Async Engine, Inputs, Utils, Worker, Config Test (CPU) # 20min
-  timeout_in_minutes: 20
+  timeout_in_minutes: 30
   mirror_hardwares: [amdexperimental, amdproduction, amdtentative]
   agent_pool: mi325_1
   grade: Blocking
@@ -73,6 +73,7 @@ steps:
   - tests/multimodal
   - tests/standalone_tests/lazy_imports.py
   - tests/tokenizers_
+  - tests/tool_parsers
   - tests/transformers_utils
   - tests/config
   no_gpu: true
@@ -82,6 +83,7 @@ steps:
   - pytest -v -s test_outputs.py
   - pytest -v -s -m 'cpu_test' multimodal
   - pytest -v -s tokenizers_
+  - pytest -v -s tool_parsers
   - pytest -v -s transformers_utils
   - pytest -v -s config
 
@@ -759,19 +761,7 @@ steps:
     - vllm/
     - tests/tool_use
   commands:
-    - pytest -v -s -m 'not cpu_test' tool_use
+    - pytest -v -s tool_use
-
-- label: OpenAI-Compatible Tool Use (CPU) # 5 mins
-  mirror_hardwares: [amdexperimental, amdproduction]
-  agent_pool: mi325_1
-  # grade: Blocking
-  timeout_in_minutes: 10
-  source_file_dependencies:
-    - vllm/
-    - tests/tool_use
-  no_gpu: true
-  commands:
-    - pytest -v -s -m 'cpu_test' tool_use
 
 #####  models test  #####
 

.buildkite/test-pipeline.yaml

@@ -57,8 +57,8 @@ steps:
   - pytest -v -s -m 'not cpu_test' multimodal
   - pytest -v -s utils_
 
-- label: Async Engine, Inputs, Utils, Worker, Config Test (CPU) # 15min
+- label: Async Engine, Inputs, Utils, Worker, Config Test (CPU) # 20min
-  timeout_in_minutes: 20
+  timeout_in_minutes: 30
   source_file_dependencies:
   - vllm/
   - tests/test_inputs.py
@@ -66,6 +66,7 @@ steps:
   - tests/multimodal
   - tests/standalone_tests/lazy_imports.py
   - tests/tokenizers_
+  - tests/tool_parsers
   - tests/transformers_utils
   - tests/config
   no_gpu: true
@@ -75,6 +76,7 @@ steps:
   - pytest -v -s test_outputs.py
   - pytest -v -s -m 'cpu_test' multimodal
   - pytest -v -s tokenizers_
+  - pytest -v -s tool_parsers
   - pytest -v -s transformers_utils
   - pytest -v -s config
 
@@ -672,16 +674,7 @@ steps:
     - vllm/
     - tests/tool_use
   commands:
-    - pytest -v -s -m 'not cpu_test' tool_use
+    - pytest -v -s tool_use
-
-- label: OpenAI-Compatible Tool Use (CPU) # 5 mins
-  timeout_in_minutes: 10
-  source_file_dependencies:
-    - vllm/
-    - tests/tool_use
-  no_gpu: true
-  commands:
-    - pytest -v -s -m 'cpu_test' tool_use
 
 #####  models test  #####
 

.buildkite/test_areas/misc.yaml

@@ -115,7 +115,7 @@ steps:
 
 - label: Async Engine, Inputs, Utils, Worker, Config (CPU)
   depends_on: ~
-  timeout_in_minutes: 20
+  timeout_in_minutes: 30
   source_file_dependencies:
   - vllm/
   - tests/test_inputs.py
@@ -123,6 +123,7 @@ steps:
   - tests/multimodal
   - tests/standalone_tests/lazy_imports.py
   - tests/tokenizers_
+  - tests/tool_parsers
   - tests/transformers_utils
   - tests/config
   no_gpu: true
@@ -132,6 +133,7 @@ steps:
   - pytest -v -s test_outputs.py
   - pytest -v -s -m 'cpu_test' multimodal
   - pytest -v -s tokenizers_
+  - pytest -v -s tool_parsers
   - pytest -v -s transformers_utils
   - pytest -v -s config
 

.buildkite/test_areas/tool_use.yaml

@@ -10,14 +10,4 @@ steps:
     - vllm/
     - tests/tool_use
   commands:
-    - pytest -v -s -m 'not cpu_test' tool_use
+    - pytest -v -s tool_use
-
-- label: OpenAI-Compatible Tool Use (CPU)
-  depends_on: ~
-  timeout_in_minutes: 10
-  source_file_dependencies:
-    - vllm/
-    - tests/tool_use
-  no_gpu: true
-  commands:
-    - pytest -v -s -m 'cpu_test' tool_use

tests/tool_parsers/test_glm4_moe_tool_parser.py

@@ -12,8 +12,6 @@ from vllm.tool_parsers.glm4_moe_tool_parser import (
     Glm4MoeModelToolParser,
 )
 
-pytestmark = pytest.mark.cpu_test
-
 pytest.skip("skip glm4_moe parser test", allow_module_level=True)
 # Use a common model that is likely to be available
 MODEL = "zai-org/GLM-4.5"

tests/tool_parsers/test_jamba_tool_parser.py

@@ -13,8 +13,6 @@ from vllm.tokenizers import TokenizerLike, get_tokenizer
 from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
 from vllm.tool_parsers.jamba_tool_parser import JambaToolParser
 
-pytestmark = pytest.mark.cpu_test
-
 MODEL = "ai21labs/Jamba-tiny-dev"
 
 

tests/tool_parsers/test_kimi_k2_tool_parser.py

@@ -10,8 +10,6 @@ from vllm.entrypoints.openai.protocol import FunctionCall, ToolCall
 from vllm.tokenizers import get_tokenizer
 from vllm.tool_parsers.kimi_k2_tool_parser import KimiK2ToolParser
 
-pytestmark = pytest.mark.cpu_test
-
 # Use a common model that is likely to be available
 MODEL = "moonshotai/Kimi-K2-Instruct"
 

tests/tool_parsers/test_minimax_tool_parser.py

@@ -15,8 +15,6 @@ from vllm.entrypoints.openai.protocol import (
 from vllm.tokenizers import get_tokenizer
 from vllm.tool_parsers.minimax_tool_parser import MinimaxToolParser
 
-pytestmark = pytest.mark.cpu_test
-
 # Use a common model that is likely to be available
 MODEL = "MiniMaxAi/MiniMax-M1-40k"
 

tests/tool_parsers/test_qwen3coder_tool_parser.py

@@ -20,8 +20,6 @@ from vllm.tool_parsers.qwen3coder_tool_parser import (
 )
 from vllm.tool_parsers.qwen3xml_tool_parser import Qwen3XMLToolParser
 
-pytestmark = pytest.mark.cpu_test
-
 MODEL = "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
 
 

tests/tool_parsers/test_seed_oss_tool_parser.py

@@ -18,8 +18,6 @@ from vllm.tokenizers import TokenizerLike, get_tokenizer
 from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
 from vllm.tool_parsers.seed_oss_tool_parser import SeedOssToolParser
 
-pytestmark = pytest.mark.cpu_test
-
 # Use a common model that is likely to be available
 MODEL = "ByteDance-Seed/Seed-OSS-36B-Instruct"
 

tests/tool_parsers/test_xlam_tool_parser.py

@@ -16,8 +16,6 @@ from vllm.tokenizers import TokenizerLike, get_tokenizer
 from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
 from vllm.tool_parsers.xlam_tool_parser import xLAMToolParser
 
-pytestmark = pytest.mark.cpu_test
-
 # Use a common model that is likely to be available
 MODEL = "Salesforce/Llama-xLAM-2-8B-fc-r"