6295d2e9bc
### What this PR does / why we need it? This pr upgrades torch-npu to 0320, so that #321, https://github.com/vllm-project/vllm-ascend/issues/267#issuecomment-2745045743 could be fixed, and #372 should be reverted after this pr ### Does this PR introduce _any_ user-facing change? upgrade torch-npu to 0320 ### How was this patch tested? tested locally with long seq inferencing. --------- Signed-off-by: MengqingCao <cmq0113@163.com>
66 lines
2.5 KiB
INI
66 lines
2.5 KiB
INI
[pytest]
|
|
minversion = 6.0
|
|
norecursedirs =
|
|
vllm-empty/tests/prefix_caching
|
|
vllm-empty/tests/weight_loading
|
|
vllm-empty/tests/samplers
|
|
vllm-empty/tests/kernels
|
|
vllm-empty/tests/quantization
|
|
vllm-empty/tests/tool_use
|
|
vllm-empty/tests/runai_model_streamer_test
|
|
vllm-empty/tests/kv_transfer
|
|
vllm-empty/tests/plugins
|
|
vllm-empty/tests/plugins_tests
|
|
vllm-empty/tests/prompt_adapter
|
|
vllm-empty/tests/compile
|
|
vllm-empty/tests/lora
|
|
vllm-empty/tests/models
|
|
vllm-empty/tests/mistral_tool_use
|
|
vllm-empty/tests/standalone_tests
|
|
vllm-empty/tests/async_engine
|
|
vllm-empty/tests/mq_llm_engine
|
|
vllm-empty/tests/tokenization
|
|
vllm-empty/tests/core
|
|
vllm-empty/tests/tracing
|
|
vllm-empty/tests/engine
|
|
vllm-empty/tests/tensorizer_loader
|
|
vllm-empty/tests/entrypoints
|
|
vllm-empty/tests/model_executor
|
|
vllm-empty/tests/encoder_decoder
|
|
vllm-empty/tests/v1
|
|
vllm-empty/tests/spec_decode
|
|
vllm-empty/tests/multi_step
|
|
vllm-empty/tests/vllm_test_utils
|
|
vllm-empty/tests/tpu
|
|
vllm-empty/tests/distributed
|
|
vllm-empty/tests/basic_correctness
|
|
vllm-empty/tests/worker
|
|
vllm-empty/tests/metrics
|
|
vllm-empty/tests/neuron
|
|
; fastsafetensors not support npu now
|
|
vllm-empty/tests/fastsafetensors_loader
|
|
|
|
addopts = --ignore=vllm-empty/tests/test_utils.py
|
|
--ignore=vllm-empty/tests/test_config.py
|
|
--ignore=vllm-empty/tests/test_scalartype.py
|
|
--ignore=vllm-empty/tests/test_embedded_commit.py
|
|
--ignore=vllm-empty/tests/test_inputs.py
|
|
--ignore=vllm-empty/tests/test_sharded_state_loader.py
|
|
--ignore=vllm-empty/tests/test_logger.py
|
|
--ignore=vllm-empty/tests/test_logits_processor.py
|
|
--ignore=vllm-empty/tests/test_regression.py
|
|
--ignore=vllm-empty/tests/models/decoder_only/language/test_aqlm.py
|
|
--ignore=vllm-empty/tests/models/decoder_only/language/test_gptq_marlin.py
|
|
--ignore=vllm-empty/tests/models/decoder_only/language/test_gptq_marlin_24.py
|
|
--ignore=vllm-empty/tests/multimodal/test_processing.py
|
|
--ignore=vllm-empty/tests/multimodal/test_processor_kwargs.py
|
|
--ignore=vllm-empty/tests/multimodal/test_utils.py
|
|
; Both V1 and V0 engine will be run in detokenizer/test_stop_reason
|
|
; VLLM_USE_V1=1 is not supported with device type=npu.
|
|
--ignore=vllm-empty/tests/detokenizer/test_stop_reason.py
|
|
; oom on llama-2-7b-hf
|
|
--ignore=vllm-empty/tests/detokenizer/test_stop_strings.py
|
|
|
|
testpaths =
|
|
vllm-empty/tests
|