xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-24 15:35:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Changing "amdproduction" allocation. (#21409)

Browse Source 
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
This commit is contained in:
Alexei-V-Ivanov-AMD 2025-07-22 22:48:31 -05:00 committed by GitHub
parent 2dec7c1a5d
commit 107111a859
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
.buildkite/test-pipeline.yaml
View File

@ -225,7 +225,7 @@ steps:
##### 1 GPU test #####
- label: Regression Test # 5min
mirror_hardwares: [amdexperimental]
mirror_hardwares: [amdexperimental, amdproduction]
source_file_dependencies:
- vllm/
- tests/test_regression
@ -277,7 +277,7 @@ steps:
- pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
- label: Examples Test # 25min
mirror_hardwares: [amdexperimental]
mirror_hardwares: [amdexperimental, amdproduction]
working_dir: "/vllm-workspace/examples"
source_file_dependencies:
- vllm/entrypoints
@ -311,7 +311,7 @@ steps:
- label: Platform Tests (CUDA)
mirror_hardwares: [amdexperimental]
mirror_hardwares: [amdexperimental, amdproduction]
source_file_dependencies:
- vllm/
- tests/cuda
@ -330,7 +330,7 @@ steps:
- VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers
- label: LoRA Test %N # 15min each
mirror_hardwares: [amdexperimental, amdproduction]
mirror_hardwares: [amdexperimental]
source_file_dependencies:
- vllm/lora
- tests/lora
@ -382,7 +382,7 @@ steps:
- pytest -v -s kernels/core
- label: Kernels Attention Test %N
mirror_hardwares: [amdexperimental, amdproduction]
mirror_hardwares: [amdexperimental]
source_file_dependencies:
- csrc/attention/
- vllm/attention
@ -393,7 +393,7 @@ steps:
parallelism: 2
- label: Kernels Quantization Test %N
mirror_hardwares: [amdexperimental, amdproduction]
mirror_hardwares: [amdexperimental]
source_file_dependencies:
- csrc/quantization/
- vllm/model_executor/layers/quantization
@ -412,7 +412,7 @@ steps:
- pytest -v -s kernels/moe
- label: Kernels Mamba Test
mirror_hardwares: [amdexperimental]
mirror_hardwares: [amdexperimental, amdproduction]
source_file_dependencies:
- csrc/mamba/
- tests/kernels/mamba
@ -420,7 +420,7 @@ steps:
- pytest -v -s kernels/mamba
- label: Tensorizer Test # 11min
mirror_hardwares: [amdexperimental]
mirror_hardwares: [amdexperimental, amdproduction]
soft_fail: true
source_file_dependencies:
- vllm/model_executor/model_loader
@ -490,7 +490,7 @@ steps:
- pytest -s entrypoints/openai/correctness/
- label: Encoder Decoder tests # 5min
mirror_hardwares: [amdexperimental]
mirror_hardwares: [amdexperimental, amdproduction]
source_file_dependencies:
- vllm/
- tests/encoder_decoder
@ -498,7 +498,7 @@ steps:
- pytest -v -s encoder_decoder
- label: OpenAI-Compatible Tool Use # 20 min
mirror_hardwares: [amdexperimental]
mirror_hardwares: [amdexperimental, amdproduction]
fast_check: false
source_file_dependencies:
- vllm/
@ -610,7 +610,7 @@ steps:
- pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=1) and not core_model'
- label: Quantized Models Test
mirror_hardwares: [amdexperimental, amdproduction]
mirror_hardwares: [amdexperimental]
source_file_dependencies:
- vllm/model_executor/layers/quantization
- tests/models/quantization